Search
Find a vulnerability
Search criteria
ⓘ
Use this form to refine search results.
Full-text search supports keyword queries with ranking and filtering.
You can combine vendor, product, and sources to narrow results.
Enable “Apply ordering” to sort by date instead of relevance.
180 vulnerabilities found for PraisonAI by MervinPraison
CVE-2026-55524 (GCVE-0-2026-55524)
Vulnerability from nvd – Published: 2026-08-05 19:58 – Updated: 2026-08-06 14:43
VLAI
EPSS
VEX
Title
PraisonAI: SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)
Summary
PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The check resolves the hostname once with socket.gethostbyname and rejects private/loopback/link-local results, but then passes the URL to a fetcher using httpx.Client(follow_redirects=True) (or urllib.request.urlopen when httpx is absent, which also follows redirects) that re-resolves the hostname at connect time with no further validation. This validate-here/fetch-there gap is exploitable through both HTTP redirects and DNS rebinding. If an attacker can influence URLs passed to web_crawl(), directly or through an agent/tool workflow, they can cause the PraisonAI host to fetch loopback, private-network, or cloud metadata endpoints reachable from that host, with the response body returned in the web_crawl() result. This issue has been fixed in version 1.6.58.
Severity
7.5 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 1.6.58
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55524",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-06T14:41:35.294289Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-06T14:43:50.259Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 1.6.58"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The check resolves the hostname once with socket.gethostbyname and rejects private/loopback/link-local results, but then passes the URL to a fetcher using httpx.Client(follow_redirects=True) (or urllib.request.urlopen when httpx is absent, which also follows redirects) that re-resolves the hostname at connect time with no further validation. This validate-here/fetch-there gap is exploitable through both HTTP redirects and DNS rebinding. If an attacker can influence URLs passed to web_crawl(), directly or through an agent/tool workflow, they can cause the PraisonAI host to fetch loopback, private-network, or cloud metadata endpoints reachable from that host, with the response body returned in the web_crawl() result. This issue has been fixed in version 1.6.58."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-367",
"description": "CWE-367: Time-of-check Time-of-use (TOCTOU) Race Condition",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:58:46.038Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj"
}
],
"source": {
"advisory": "GHSA-vg6p-v9vm-6fgj",
"discovery": "UNKNOWN"
},
"title": "PraisonAI: SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55524",
"datePublished": "2026-08-05T19:58:46.038Z",
"dateReserved": "2026-06-16T22:44:22.284Z",
"dateUpdated": "2026-08-06T14:43:50.259Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55523 (GCVE-0-2026-55523)
Vulnerability from nvd – Published: 2026-08-05 19:26 – Updated: 2026-08-06 14:38
VLAI
EPSS
VEX
Title
PraisonAI has a`web_crawl` SSRF protection bypass via unchecked redirect targets
Summary
PraisonAI is a multi-agent teams system. In versions 1.5.128 through 1.6.57, the praisonaiagents.tools.web_crawl_tools.web_crawl() function is vulnerable to server-side request forgery. While it validates the initially supplied URL and blocks direct loopback and private destinations, its default httpx fallback uses httpx.Client(follow_redirects=True) and does not revalidate intermediate or final redirect targets. An attacker who can influence a URL passed to web_crawl(), directly or through an agent or tool workflow, can supply an attacker-controlled public URL that passes the initial host check and then redirects to loopback, private-network, or cloud metadata endpoints reachable from the host, with the redirected response body returned in the web_crawl() result. This constitutes an incomplete fix and patch bypass for the previously disclosed web_crawl SSRF class (GHSA-qq9r-63f6-v542 / CVE-2026-40160 and GHSA-8f4v-xfm9-3244), since the guard validates only the requested URL and not the destination actually fetched after redirection. This issue has been fixed in version 1.6.58.
Severity
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
>= 1.5.128, < 1.6.58
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55523",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-06T14:36:55.390565Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-06T14:38:08.242Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8hjw-25cg-g52h"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.5.128, \u003c 1.6.58"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions 1.5.128 through 1.6.57, the praisonaiagents.tools.web_crawl_tools.web_crawl() function is vulnerable to server-side request forgery. While it validates the initially supplied URL and blocks direct loopback and private destinations, its default httpx fallback uses httpx.Client(follow_redirects=True) and does not revalidate intermediate or final redirect targets. An attacker who can influence a URL passed to web_crawl(), directly or through an agent or tool workflow, can supply an attacker-controlled public URL that passes the initial host check and then redirects to loopback, private-network, or cloud metadata endpoints reachable from the host, with the redirected response body returned in the web_crawl() result. This constitutes an incomplete fix and patch bypass for the previously disclosed web_crawl SSRF class (GHSA-qq9r-63f6-v542 / CVE-2026-40160 and GHSA-8f4v-xfm9-3244), since the guard validates only the requested URL and not the destination actually fetched after redirection. This issue has been fixed in version 1.6.58."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 7.7,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:26:22.324Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8hjw-25cg-g52h",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8hjw-25cg-g52h"
}
],
"source": {
"advisory": "GHSA-8hjw-25cg-g52h",
"discovery": "UNKNOWN"
},
"title": "PraisonAI has a`web_crawl` SSRF protection bypass via unchecked redirect targets"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55523",
"datePublished": "2026-08-05T19:26:22.324Z",
"dateReserved": "2026-06-16T22:44:22.284Z",
"dateUpdated": "2026-08-06T14:38:08.242Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55522 (GCVE-0-2026-55522)
Vulnerability from nvd – Published: 2026-08-05 19:01 – Updated: 2026-08-06 18:45
VLAI
EPSS
VEX
Title
PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code
Summary
PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow "include" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe's tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.
Severity
7.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
>= 3.9.26, < 4.6.58
|
|
| MervinPraison | praisonaiagents |
Affected:
>= 0.12.12, < 1.6.58
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55522",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-06T18:43:28.382511Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-06T18:45:05.648Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003e= 3.9.26, \u003c 4.6.58"
}
]
},
{
"product": "praisonaiagents",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003e= 0.12.12, \u003c 1.6.58"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow \"include\" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe\u0027s tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-426",
"description": "CWE-426: Untrusted Search Path",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-829",
"description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:01:43.051Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc"
}
],
"source": {
"advisory": "GHSA-hxmv-c4g6-5fqc",
"discovery": "UNKNOWN"
},
"title": "PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55522",
"datePublished": "2026-08-05T19:01:43.051Z",
"dateReserved": "2026-06-16T22:44:22.284Z",
"dateUpdated": "2026-08-06T18:45:05.648Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-48168 (GCVE-0-2026-48168)
Vulnerability from nvd – Published: 2026-08-05 18:29 – Updated: 2026-08-05 19:24
VLAI
EPSS
VEX
Title
PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name
Summary
PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow allows any @claude comment to trigger the job regardless of whether the commenter is a trusted collaborator. An outside contributor can open a pull request from a fork whose branch name contains shell metacharacters and comment @claude, causing Bash to execute arbitrary shell code in the GitHub Actions runner. Because these commands run in a job holding a GitHub App token with write permissions, OIDC access, and gh/git access, the injection can be chained through $GITHUB_PATH to compromise later privileged steps, enabling repository writes, pull request and issue manipulation, or OIDC-token abuse. This issue has been fixed in version 4.6.40.
Severity
10 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-862 - Missing Authorization
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-48168",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-05T19:23:57.492283Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:24:05.128Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xp85-6wwf-r67c"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow allows any @claude comment to trigger the job regardless of whether the commenter is a trusted collaborator. An outside contributor can open a pull request from a fork whose branch name contains shell metacharacters and comment @claude, causing Bash to execute arbitrary shell code in the GitHub Actions runner. Because these commands run in a job holding a GitHub App token with write permissions, OIDC access, and gh/git access, the injection can be chained through $GITHUB_PATH to compromise later privileged steps, enabling repository writes, pull request and issue manipulation, or OIDC-token abuse. This issue has been fixed in version 4.6.40."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 10,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T18:29:38.632Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xp85-6wwf-r67c",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xp85-6wwf-r67c"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/179cab02dbec0c1e9b601507a659",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/179cab02dbec0c1e9b601507a659"
}
],
"source": {
"advisory": "GHSA-xp85-6wwf-r67c",
"discovery": "UNKNOWN"
},
"title": "PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-48168",
"datePublished": "2026-08-05T18:29:38.632Z",
"dateReserved": "2026-05-20T23:12:43.032Z",
"dateUpdated": "2026-08-05T19:24:05.128Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47405 (GCVE-0-2026-47405)
Vulnerability from nvd – Published: 2026-07-21 16:18 – Updated: 2026-07-21 17:59
VLAI
EPSS
VEX
Title
PraisonAI Platform missing role checks let any workspace member become owner and take over workspace membership
Summary
PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have a broken workspace authorization check that allows any authenticated low-privilege workspace member to escalate their own role to `owner`. The issue is caused by privileged workspace-management routes using the shared dependency `require_workspace_member(...)` without requiring `admin` or `owner`. The dependency defaults to `min_role="member"`, so routes that should be administrative are accessible to ordinary workspace members. As a result, a normal workspace member can promote their own account from `member` to `owner`; add arbitrary users as `owner` or `admin`; change other members' roles; remove legitimate owners or members; take over workspace membership completely; and/or perform destructive workspace operations after escalation. This is a broken access control / vertical privilege escalation vulnerability. PraisonAI Platform version 0.1.4 patches the issue.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1686 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | praisonai-platform |
Affected:
< 0.1.4
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47405",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T17:58:53.628161Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:59:03.862Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h37g-4h4p-9x97"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "praisonai-platform",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 0.1.4"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have a broken workspace authorization check that allows any authenticated low-privilege workspace member to escalate their own role to `owner`. The issue is caused by privileged workspace-management routes using the shared dependency `require_workspace_member(...)` without requiring `admin` or `owner`. The dependency defaults to `min_role=\"member\"`, so routes that should be administrative are accessible to ordinary workspace members. As a result, a normal workspace member can promote their own account from `member` to `owner`; add arbitrary users as `owner` or `admin`; change other members\u0027 roles; remove legitimate owners or members; take over workspace membership completely; and/or perform destructive workspace operations after escalation. This is a broken access control / vertical privilege escalation vulnerability. PraisonAI Platform version 0.1.4 patches the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-284",
"description": "CWE-284: Improper Access Control",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:22:15.425Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h37g-4h4p-9x97",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h37g-4h4p-9x97"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1686",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1686"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47"
}
],
"source": {
"advisory": "GHSA-h37g-4h4p-9x97",
"discovery": "UNKNOWN"
},
"title": "PraisonAI Platform missing role checks let any workspace member become owner and take over workspace membership"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47405",
"datePublished": "2026-07-21T16:18:27.991Z",
"dateReserved": "2026-05-19T19:37:43.525Z",
"dateUpdated": "2026-07-21T17:59:03.862Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47399 (GCVE-0-2026-47399)
Vulnerability from nvd – Published: 2026-07-21 16:15 – Updated: 2026-07-22 14:36
VLAI
EPSS
VEX
Title
PraisonAI Platform workspace-scoped routes allow cross-workspace object access by global object ID
Summary
PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Prior to version 0.1.4, the workspace-scoped REST routes contain a systemic object-level authorization flaw that allows an authenticated user from one workspace to access, modify, and delete objects belonging to another workspace by supplying the victim object's global UUID. The affected pattern appears in workspace-scoped routes such as agents, projects, issues, and comments. The route layer verifies that the caller is a member of the `workspace_id` provided in the URL, but the service layer later resolves the target object by global object ID only. It does not verify that the resolved object actually belongs to the workspace in the URL. As a result, a valid member of `workspace_attacker` can call a route under `/api/v1/workspaces/{workspace_attacker}/...` while supplying an object UUID from `workspace_victim`. The server authorizes the request based on membership in `workspace_attacker`, then fetches or mutates the victim object by global UUID. This breaks the platform's workspace isolation boundary. PraisonAI Platform version 0.1.4 patches the issue.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1686 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | praisonai-platform |
Affected:
< 0.1.4
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47399",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:36:05.907729Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:36:30.296Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6h6v-6m7w-7vxx"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "praisonai-platform",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 0.1.4"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Prior to version 0.1.4, the workspace-scoped REST routes contain a systemic object-level authorization flaw that allows an authenticated user from one workspace to access, modify, and delete objects belonging to another workspace by supplying the victim object\u0027s global UUID. The affected pattern appears in workspace-scoped routes such as agents, projects, issues, and comments. The route layer verifies that the caller is a member of the `workspace_id` provided in the URL, but the service layer later resolves the target object by global object ID only. It does not verify that the resolved object actually belongs to the workspace in the URL. As a result, a valid member of `workspace_attacker` can call a route under `/api/v1/workspaces/{workspace_attacker}/...` while supplying an object UUID from `workspace_victim`. The server authorizes the request based on membership in `workspace_attacker`, then fetches or mutates the victim object by global UUID. This breaks the platform\u0027s workspace isolation boundary. PraisonAI Platform version 0.1.4 patches the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-284",
"description": "CWE-284: Improper Access Control",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-639",
"description": "CWE-639: Authorization Bypass Through User-Controlled Key",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:22:27.419Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6h6v-6m7w-7vxx",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6h6v-6m7w-7vxx"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1686",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1686"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47"
}
],
"source": {
"advisory": "GHSA-6h6v-6m7w-7vxx",
"discovery": "UNKNOWN"
},
"title": "PraisonAI Platform workspace-scoped routes allow cross-workspace object access by global object ID"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47399",
"datePublished": "2026-07-21T16:15:09.882Z",
"dateReserved": "2026-05-19T19:22:45.730Z",
"dateUpdated": "2026-07-22T14:36:30.296Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47398 (GCVE-0-2026-47398)
Vulnerability from nvd – Published: 2026-07-21 16:01 – Updated: 2026-07-21 16:33
VLAI
EPSS
VEX
Title
PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334
Summary
PraisonAI is a multi-agent teams system. The v4.6.32 chokepoint refactor (which patched CVE-2026-44334 / GHSA-xcmw-grxf-wjhj) added the PRAISONAI_ALLOW_LOCAL_TOOLS env-var gate to the tool_override.py sinks. However, two additional spec.loader.exec_module call sites in praisonai/agents_generator.py were missed and remain completely unguarded in versions prior to 4.6.40. Both functions accept a module_path parameter sourced from YAML configuration and execute it without validation, signature checking, or the env-var gate. Version 4.6.40 fixes the issue.
Severity
8.1 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1685 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47398",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T16:33:17.988858Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:33:53.371Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-78r8-wwqv-r299"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. The v4.6.32 chokepoint refactor (which patched CVE-2026-44334 / GHSA-xcmw-grxf-wjhj) added the PRAISONAI_ALLOW_LOCAL_TOOLS env-var gate to the tool_override.py sinks. However, two additional spec.loader.exec_module call sites in praisonai/agents_generator.py were missed and remain completely unguarded in versions prior to 4.6.40. Both functions accept a module_path parameter sourced from YAML configuration and execute it without validation, signature checking, or the env-var gate. Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.1,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-829",
"description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:01:22.037Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-78r8-wwqv-r299",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-78r8-wwqv-r299"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1685",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1685"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619"
}
],
"source": {
"advisory": "GHSA-78r8-wwqv-r299",
"discovery": "UNKNOWN"
},
"title": "PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47398",
"datePublished": "2026-07-21T16:01:22.037Z",
"dateReserved": "2026-05-19T19:22:45.730Z",
"dateUpdated": "2026-07-21T16:33:53.371Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47397 (GCVE-0-2026-47397)
Vulnerability from nvd – Published: 2026-07-21 15:57 – Updated: 2026-07-23 14:25
VLAI
EPSS
VEX
Title
PraisonAI has an Arbitrary File Write in Python API
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. `write_file` skips path validation when `workspace=None` (always `None` in production). Version 4.6.40 fixes the issue.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47397",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-23T14:25:47.720177Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T14:25:50.782Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hvhp-v2gc-268q"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. `write_file` skips path validation when `workspace=None` (always `None` in production). Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 7.1,
"baseSeverity": "HIGH",
"privilegesRequired": "LOW",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:57:25.695Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hvhp-v2gc-268q",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hvhp-v2gc-268q"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-hvhp-v2gc-268q",
"discovery": "UNKNOWN"
},
"title": "PraisonAI has an Arbitrary File Write in Python API"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47397",
"datePublished": "2026-07-21T15:57:25.695Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-23T14:25:50.782Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47396 (GCVE-0-2026-47396)
Vulnerability from nvd – Published: 2026-07-21 15:55 – Updated: 2026-07-22 14:13
VLAI
EPSS
VEX
Title
PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token allows any reachable client to list agents, inspect agent metadata and instructions, invoke agents, and unregister agents. This is security-relevant because the bundled call server includes the vulnerable router and binds to `0.0.0.0`. As a result, operators who launch the call server without explicitly setting `CALL_SERVER_TOKEN` may unintentionally expose an unauthenticated remote agent control plane. Version 4.6.40 fixes the issue.
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47396",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:13:08.439122Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:13:42.099Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-86qc-r5v2-v6x6"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI\u0027s call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token allows any reachable client to list agents, inspect agent metadata and instructions, invoke agents, and unregister agents. This is security-relevant because the bundled call server includes the vulnerable router and binds to `0.0.0.0`. As a result, operators who launch the call server without explicitly setting `CALL_SERVER_TOKEN` may unintentionally expose an unauthenticated remote agent control plane. Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-284",
"description": "CWE-284: Improper Access Control",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:55:22.599Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-86qc-r5v2-v6x6",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-86qc-r5v2-v6x6"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619"
}
],
"source": {
"advisory": "GHSA-86qc-r5v2-v6x6",
"discovery": "UNKNOWN"
},
"title": "PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47396",
"datePublished": "2026-07-21T15:55:22.599Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-22T14:13:42.099Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47395 (GCVE-0-2026-47395)
Vulnerability from nvd – Published: 2026-07-21 15:52 – Updated: 2026-07-21 17:15
VLAI
EPSS
VEX
Title
PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.
Severity
5.5 (Medium)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
|
| MervinPraison | praisonaiagents |
Affected:
< 1.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47395",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T17:09:32.354388Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:15:13.196Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
},
{
"product": "praisonaiagents",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 1.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI\u0027s direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:\u003chttp-or-https-url\u003e`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator\u0027s machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 5.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-200",
"description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:52:52.682Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-5cxw-77wg-jrf3",
"discovery": "UNKNOWN"
},
"title": "PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47395",
"datePublished": "2026-07-21T15:52:52.682Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-21T17:15:13.196Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47394 (GCVE-0-2026-47394)
Vulnerability from nvd – Published: 2026-07-21 15:44 – Updated: 2026-07-21 18:01
VLAI
EPSS
VEX
Title
PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` ("fix(security): harden MCP rules path handling…") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pattern, `workflow.validate` and `deploy.validate`. Neither was mentioned in the original advisory. Both remained unchanged. The original advisory also identified the dispatcher (`server.py:281-298`) as a root cause. It accepts unvalidated `**kwargs` from `params["arguments"]` with no enforcement against the tool's declared `input_schema`. That code is unchanged prior to version 4.6.40. A single unauthenticated MCP `tools/call` to `praisonai.workflow.show` returns the contents of any file the host user can read: `/etc/passwd`, `~/.ssh/id_rsa`, `~/.aws/credentials`, or any project `.env`. Version 4.6.40 contains an updated fix.
Severity
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47394",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T18:00:46.506651Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T18:01:03.736Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9cr9-25q5-8prj"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` (\"fix(security): harden MCP rules path handling\u2026\") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pattern, `workflow.validate` and `deploy.validate`. Neither was mentioned in the original advisory. Both remained unchanged. The original advisory also identified the dispatcher (`server.py:281-298`) as a root cause. It accepts unvalidated `**kwargs` from `params[\"arguments\"]` with no enforcement against the tool\u0027s declared `input_schema`. That code is unchanged prior to version 4.6.40. A single unauthenticated MCP `tools/call` to `praisonai.workflow.show` returns the contents of any file the host user can read: `/etc/passwd`, `~/.ssh/id_rsa`, `~/.aws/credentials`, or any project `.env`. Version 4.6.40 contains an updated fix."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "NONE"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-200",
"description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:44:36.292Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9cr9-25q5-8prj",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9cr9-25q5-8prj"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-9cr9-25q5-8prj",
"discovery": "UNKNOWN"
},
"title": "PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47394",
"datePublished": "2026-07-21T15:44:36.292Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-21T18:01:03.736Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47393 (GCVE-0-2026-47393)
Vulnerability from nvd – Published: 2026-07-21 15:39 – Updated: 2026-07-22 14:34
VLAI
EPSS
VEX
Title
PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default
Summary
PraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_api_server_code`) that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart (`praisonai deploy --type api`) get a server that binds to `0.0.0.0` per the recommended sample YAML, exposes `/chat` and `/agents` endpoints, runs `praisonai.run()` on user-supplied JSON input — LLM orchestration with the API key materials present in the process environment, and does not require any authentication. Versions prior to 4.6.40 still ship the generator with `auth_enabled` defaulting to `False`. The fix shape is opt-in via `APIConfig(auth_enabled=True, auth_token=...)`. Version 4.6.40 fixes the issue.
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1685 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
| https://github.com/advisories/GHSA-6rmh-7xcm-cpxj | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47393",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:33:44.826949Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:34:05.072Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8444-4fhq-fxpq"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_api_server_code`) that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart (`praisonai deploy --type api`) get a server that binds to `0.0.0.0` per the recommended sample YAML, exposes `/chat` and `/agents` endpoints, runs `praisonai.run()` on user-supplied JSON input \u2014 LLM orchestration with the API key materials present in the process environment, and does not require any authentication. Versions prior to 4.6.40 still ship the generator with `auth_enabled` defaulting to `False`. The fix shape is opt-in via `APIConfig(auth_enabled=True, auth_token=...)`. Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-1188",
"description": "CWE-1188: Insecure Default Initialization of Resource",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:39:28.459Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8444-4fhq-fxpq",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8444-4fhq-fxpq"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1685",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1685"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619"
},
{
"name": "https://github.com/advisories/GHSA-6rmh-7xcm-cpxj",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/advisories/GHSA-6rmh-7xcm-cpxj"
}
],
"source": {
"advisory": "GHSA-8444-4fhq-fxpq",
"discovery": "UNKNOWN"
},
"title": "PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47393",
"datePublished": "2026-07-21T15:39:28.459Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-22T14:34:05.072Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47392 (GCVE-0-2026-47392)
Vulnerability from nvd – Published: 2026-07-21 15:27 – Updated: 2026-07-21 16:39
VLAI
EPSS
VEX
Title
PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. This is a novel bypass that survives all patches for CVE-2026-39888 (frame traversal), CVE-2026-34938 (str subclass), and CVE-2026-40158 (`type.__getattribute__` trampoline). PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain an updated fix.
Severity
9.9 (Critical)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
|
| MervinPraison | < 1.6.40 |
Affected:
praisonaiagents
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47392",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T16:39:00.607801Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:39:40.246Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
},
{
"product": "\u003c 1.6.40",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "praisonaiagents"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. This is a novel bypass that survives all patches for CVE-2026-39888 (frame traversal), CVE-2026-34938 (str subclass), and CVE-2026-40158 (`type.__getattribute__` trampoline). PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain an updated fix."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.9,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-184",
"description": "CWE-184: Incomplete List of Disallowed Inputs",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-693",
"description": "CWE-693: Protection Mechanism Failure",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:52:22.329Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-4mr5-g6f9-cfrh",
"discovery": "UNKNOWN"
},
"title": "PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47392",
"datePublished": "2026-07-21T15:27:16.557Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-21T16:39:40.246Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47391 (GCVE-0-2026-47391)
Vulnerability from nvd – Published: 2026-07-21 15:21 – Updated: 2026-07-23 14:27
VLAI
EPSS
VEX
Title
PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue.
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1793 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47391",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-23T14:27:02.928342Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T14:27:07.049Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI\u0027s first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-95",
"description": "CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:21:22.916Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1793",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1793"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747"
}
],
"source": {
"advisory": "GHSA-vg22-4gmj-prxw",
"discovery": "UNKNOWN"
},
"title": "PraisonAI\u0027s unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47391",
"datePublished": "2026-07-21T15:21:22.916Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-23T14:27:07.049Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47390 (GCVE-0-2026-47390)
Vulnerability from nvd – Published: 2026-07-21 14:47 – Updated: 2026-07-22 14:10
VLAI
EPSS
VEX
Title
PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `spider_tools` URL validation can be bypassed using alternate loopback host encodings. The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled URLs. However, the validation only blocks a small set of exact host strings such as `localhost` and `127.0.0.1`. It does not normalize hostnames, resolve DNS, parse numeric IPv4 variants, or validate the final resolved IP address before making the request. As a result, certain URLs may bypass the protection and still reach loopback services. After the weak validation passes, `scrape_page()` calls `requests.Session.get()` on the attacker-controlled URL. This allows an attacker who can influence URLs passed to `scrape_page`, `crawl`, or `extract_text` to induce SSRF requests against loopback-only services. This is a server-side request forgery protection bypass. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a patch.
Severity
5.5 (Medium)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
|
| MervinPraison | praisonaiagents |
Affected:
< 1.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47390",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:08:40.990468Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:10:08.532Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5c6w-wwfq-7qqm"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
},
{
"product": "praisonaiagents",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 1.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `spider_tools` URL validation can be bypassed using alternate loopback host encodings. The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled URLs. However, the validation only blocks a small set of exact host strings such as `localhost` and `127.0.0.1`. It does not normalize hostnames, resolve DNS, parse numeric IPv4 variants, or validate the final resolved IP address before making the request. As a result, certain URLs may bypass the protection and still reach loopback services. After the weak validation passes, `scrape_page()` calls `requests.Session.get()` on the attacker-controlled URL. This allows an attacker who can influence URLs passed to `scrape_page`, `crawl`, or `extract_text` to induce SSRF requests against loopback-only services. This is a server-side request forgery protection bypass. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a patch."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 5.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T14:47:53.059Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5c6w-wwfq-7qqm",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5c6w-wwfq-7qqm"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-5c6w-wwfq-7qqm",
"discovery": "UNKNOWN"
},
"title": "PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47390",
"datePublished": "2026-07-21T14:47:53.059Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-22T14:10:08.532Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55524 (GCVE-0-2026-55524)
Vulnerability from cvelistv5 – Published: 2026-08-05 19:58 – Updated: 2026-08-06 14:43
VLAI
EPSS
VEX
Title
PraisonAI: SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)
Summary
PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The check resolves the hostname once with socket.gethostbyname and rejects private/loopback/link-local results, but then passes the URL to a fetcher using httpx.Client(follow_redirects=True) (or urllib.request.urlopen when httpx is absent, which also follows redirects) that re-resolves the hostname at connect time with no further validation. This validate-here/fetch-there gap is exploitable through both HTTP redirects and DNS rebinding. If an attacker can influence URLs passed to web_crawl(), directly or through an agent/tool workflow, they can cause the PraisonAI host to fetch loopback, private-network, or cloud metadata endpoints reachable from that host, with the response body returned in the web_crawl() result. This issue has been fixed in version 1.6.58.
Severity
7.5 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 1.6.58
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55524",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-06T14:41:35.294289Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-06T14:43:50.259Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 1.6.58"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The check resolves the hostname once with socket.gethostbyname and rejects private/loopback/link-local results, but then passes the URL to a fetcher using httpx.Client(follow_redirects=True) (or urllib.request.urlopen when httpx is absent, which also follows redirects) that re-resolves the hostname at connect time with no further validation. This validate-here/fetch-there gap is exploitable through both HTTP redirects and DNS rebinding. If an attacker can influence URLs passed to web_crawl(), directly or through an agent/tool workflow, they can cause the PraisonAI host to fetch loopback, private-network, or cloud metadata endpoints reachable from that host, with the response body returned in the web_crawl() result. This issue has been fixed in version 1.6.58."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-367",
"description": "CWE-367: Time-of-check Time-of-use (TOCTOU) Race Condition",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:58:46.038Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj"
}
],
"source": {
"advisory": "GHSA-vg6p-v9vm-6fgj",
"discovery": "UNKNOWN"
},
"title": "PraisonAI: SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55524",
"datePublished": "2026-08-05T19:58:46.038Z",
"dateReserved": "2026-06-16T22:44:22.284Z",
"dateUpdated": "2026-08-06T14:43:50.259Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55523 (GCVE-0-2026-55523)
Vulnerability from cvelistv5 – Published: 2026-08-05 19:26 – Updated: 2026-08-06 14:38
VLAI
EPSS
VEX
Title
PraisonAI has a`web_crawl` SSRF protection bypass via unchecked redirect targets
Summary
PraisonAI is a multi-agent teams system. In versions 1.5.128 through 1.6.57, the praisonaiagents.tools.web_crawl_tools.web_crawl() function is vulnerable to server-side request forgery. While it validates the initially supplied URL and blocks direct loopback and private destinations, its default httpx fallback uses httpx.Client(follow_redirects=True) and does not revalidate intermediate or final redirect targets. An attacker who can influence a URL passed to web_crawl(), directly or through an agent or tool workflow, can supply an attacker-controlled public URL that passes the initial host check and then redirects to loopback, private-network, or cloud metadata endpoints reachable from the host, with the redirected response body returned in the web_crawl() result. This constitutes an incomplete fix and patch bypass for the previously disclosed web_crawl SSRF class (GHSA-qq9r-63f6-v542 / CVE-2026-40160 and GHSA-8f4v-xfm9-3244), since the guard validates only the requested URL and not the destination actually fetched after redirection. This issue has been fixed in version 1.6.58.
Severity
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
>= 1.5.128, < 1.6.58
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55523",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-06T14:36:55.390565Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-06T14:38:08.242Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8hjw-25cg-g52h"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.5.128, \u003c 1.6.58"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions 1.5.128 through 1.6.57, the praisonaiagents.tools.web_crawl_tools.web_crawl() function is vulnerable to server-side request forgery. While it validates the initially supplied URL and blocks direct loopback and private destinations, its default httpx fallback uses httpx.Client(follow_redirects=True) and does not revalidate intermediate or final redirect targets. An attacker who can influence a URL passed to web_crawl(), directly or through an agent or tool workflow, can supply an attacker-controlled public URL that passes the initial host check and then redirects to loopback, private-network, or cloud metadata endpoints reachable from the host, with the redirected response body returned in the web_crawl() result. This constitutes an incomplete fix and patch bypass for the previously disclosed web_crawl SSRF class (GHSA-qq9r-63f6-v542 / CVE-2026-40160 and GHSA-8f4v-xfm9-3244), since the guard validates only the requested URL and not the destination actually fetched after redirection. This issue has been fixed in version 1.6.58."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 7.7,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:26:22.324Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8hjw-25cg-g52h",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8hjw-25cg-g52h"
}
],
"source": {
"advisory": "GHSA-8hjw-25cg-g52h",
"discovery": "UNKNOWN"
},
"title": "PraisonAI has a`web_crawl` SSRF protection bypass via unchecked redirect targets"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55523",
"datePublished": "2026-08-05T19:26:22.324Z",
"dateReserved": "2026-06-16T22:44:22.284Z",
"dateUpdated": "2026-08-06T14:38:08.242Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55522 (GCVE-0-2026-55522)
Vulnerability from cvelistv5 – Published: 2026-08-05 19:01 – Updated: 2026-08-06 18:45
VLAI
EPSS
VEX
Title
PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code
Summary
PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow "include" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe's tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.
Severity
7.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
>= 3.9.26, < 4.6.58
|
|
| MervinPraison | praisonaiagents |
Affected:
>= 0.12.12, < 1.6.58
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55522",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-06T18:43:28.382511Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-06T18:45:05.648Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003e= 3.9.26, \u003c 4.6.58"
}
]
},
{
"product": "praisonaiagents",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003e= 0.12.12, \u003c 1.6.58"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow \"include\" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe\u0027s tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-426",
"description": "CWE-426: Untrusted Search Path",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-829",
"description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:01:43.051Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc"
}
],
"source": {
"advisory": "GHSA-hxmv-c4g6-5fqc",
"discovery": "UNKNOWN"
},
"title": "PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55522",
"datePublished": "2026-08-05T19:01:43.051Z",
"dateReserved": "2026-06-16T22:44:22.284Z",
"dateUpdated": "2026-08-06T18:45:05.648Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-48168 (GCVE-0-2026-48168)
Vulnerability from cvelistv5 – Published: 2026-08-05 18:29 – Updated: 2026-08-05 19:24
VLAI
EPSS
VEX
Title
PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name
Summary
PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow allows any @claude comment to trigger the job regardless of whether the commenter is a trusted collaborator. An outside contributor can open a pull request from a fork whose branch name contains shell metacharacters and comment @claude, causing Bash to execute arbitrary shell code in the GitHub Actions runner. Because these commands run in a job holding a GitHub App token with write permissions, OIDC access, and gh/git access, the injection can be chained through $GITHUB_PATH to compromise later privileged steps, enabling repository writes, pull request and issue manipulation, or OIDC-token abuse. This issue has been fixed in version 4.6.40.
Severity
10 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-862 - Missing Authorization
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-48168",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-05T19:23:57.492283Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T19:24:05.128Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xp85-6wwf-r67c"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull request branch name into a Bash run: block without quoting or validation. Additionally, the workflow allows any @claude comment to trigger the job regardless of whether the commenter is a trusted collaborator. An outside contributor can open a pull request from a fork whose branch name contains shell metacharacters and comment @claude, causing Bash to execute arbitrary shell code in the GitHub Actions runner. Because these commands run in a job holding a GitHub App token with write permissions, OIDC access, and gh/git access, the injection can be chained through $GITHUB_PATH to compromise later privileged steps, enabling repository writes, pull request and issue manipulation, or OIDC-token abuse. This issue has been fixed in version 4.6.40."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 10,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-05T18:29:38.632Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xp85-6wwf-r67c",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xp85-6wwf-r67c"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/179cab02dbec0c1e9b601507a659",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/179cab02dbec0c1e9b601507a659"
}
],
"source": {
"advisory": "GHSA-xp85-6wwf-r67c",
"discovery": "UNKNOWN"
},
"title": "PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-48168",
"datePublished": "2026-08-05T18:29:38.632Z",
"dateReserved": "2026-05-20T23:12:43.032Z",
"dateUpdated": "2026-08-05T19:24:05.128Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47405 (GCVE-0-2026-47405)
Vulnerability from cvelistv5 – Published: 2026-07-21 16:18 – Updated: 2026-07-21 17:59
VLAI
EPSS
VEX
Title
PraisonAI Platform missing role checks let any workspace member become owner and take over workspace membership
Summary
PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have a broken workspace authorization check that allows any authenticated low-privilege workspace member to escalate their own role to `owner`. The issue is caused by privileged workspace-management routes using the shared dependency `require_workspace_member(...)` without requiring `admin` or `owner`. The dependency defaults to `min_role="member"`, so routes that should be administrative are accessible to ordinary workspace members. As a result, a normal workspace member can promote their own account from `member` to `owner`; add arbitrary users as `owner` or `admin`; change other members' roles; remove legitimate owners or members; take over workspace membership completely; and/or perform destructive workspace operations after escalation. This is a broken access control / vertical privilege escalation vulnerability. PraisonAI Platform version 0.1.4 patches the issue.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1686 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | praisonai-platform |
Affected:
< 0.1.4
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47405",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T17:58:53.628161Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:59:03.862Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h37g-4h4p-9x97"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "praisonai-platform",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 0.1.4"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have a broken workspace authorization check that allows any authenticated low-privilege workspace member to escalate their own role to `owner`. The issue is caused by privileged workspace-management routes using the shared dependency `require_workspace_member(...)` without requiring `admin` or `owner`. The dependency defaults to `min_role=\"member\"`, so routes that should be administrative are accessible to ordinary workspace members. As a result, a normal workspace member can promote their own account from `member` to `owner`; add arbitrary users as `owner` or `admin`; change other members\u0027 roles; remove legitimate owners or members; take over workspace membership completely; and/or perform destructive workspace operations after escalation. This is a broken access control / vertical privilege escalation vulnerability. PraisonAI Platform version 0.1.4 patches the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-284",
"description": "CWE-284: Improper Access Control",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:22:15.425Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h37g-4h4p-9x97",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h37g-4h4p-9x97"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1686",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1686"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47"
}
],
"source": {
"advisory": "GHSA-h37g-4h4p-9x97",
"discovery": "UNKNOWN"
},
"title": "PraisonAI Platform missing role checks let any workspace member become owner and take over workspace membership"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47405",
"datePublished": "2026-07-21T16:18:27.991Z",
"dateReserved": "2026-05-19T19:37:43.525Z",
"dateUpdated": "2026-07-21T17:59:03.862Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47399 (GCVE-0-2026-47399)
Vulnerability from cvelistv5 – Published: 2026-07-21 16:15 – Updated: 2026-07-22 14:36
VLAI
EPSS
VEX
Title
PraisonAI Platform workspace-scoped routes allow cross-workspace object access by global object ID
Summary
PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Prior to version 0.1.4, the workspace-scoped REST routes contain a systemic object-level authorization flaw that allows an authenticated user from one workspace to access, modify, and delete objects belonging to another workspace by supplying the victim object's global UUID. The affected pattern appears in workspace-scoped routes such as agents, projects, issues, and comments. The route layer verifies that the caller is a member of the `workspace_id` provided in the URL, but the service layer later resolves the target object by global object ID only. It does not verify that the resolved object actually belongs to the workspace in the URL. As a result, a valid member of `workspace_attacker` can call a route under `/api/v1/workspaces/{workspace_attacker}/...` while supplying an object UUID from `workspace_victim`. The server authorizes the request based on membership in `workspace_attacker`, then fetches or mutates the victim object by global UUID. This breaks the platform's workspace isolation boundary. PraisonAI Platform version 0.1.4 patches the issue.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1686 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | praisonai-platform |
Affected:
< 0.1.4
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47399",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:36:05.907729Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:36:30.296Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6h6v-6m7w-7vxx"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "praisonai-platform",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 0.1.4"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Prior to version 0.1.4, the workspace-scoped REST routes contain a systemic object-level authorization flaw that allows an authenticated user from one workspace to access, modify, and delete objects belonging to another workspace by supplying the victim object\u0027s global UUID. The affected pattern appears in workspace-scoped routes such as agents, projects, issues, and comments. The route layer verifies that the caller is a member of the `workspace_id` provided in the URL, but the service layer later resolves the target object by global object ID only. It does not verify that the resolved object actually belongs to the workspace in the URL. As a result, a valid member of `workspace_attacker` can call a route under `/api/v1/workspaces/{workspace_attacker}/...` while supplying an object UUID from `workspace_victim`. The server authorizes the request based on membership in `workspace_attacker`, then fetches or mutates the victim object by global UUID. This breaks the platform\u0027s workspace isolation boundary. PraisonAI Platform version 0.1.4 patches the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-284",
"description": "CWE-284: Improper Access Control",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-639",
"description": "CWE-639: Authorization Bypass Through User-Controlled Key",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:22:27.419Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6h6v-6m7w-7vxx",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6h6v-6m7w-7vxx"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1686",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1686"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/24385d64876577620f749957bd4814f162f4ca47"
}
],
"source": {
"advisory": "GHSA-6h6v-6m7w-7vxx",
"discovery": "UNKNOWN"
},
"title": "PraisonAI Platform workspace-scoped routes allow cross-workspace object access by global object ID"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47399",
"datePublished": "2026-07-21T16:15:09.882Z",
"dateReserved": "2026-05-19T19:22:45.730Z",
"dateUpdated": "2026-07-22T14:36:30.296Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47398 (GCVE-0-2026-47398)
Vulnerability from cvelistv5 – Published: 2026-07-21 16:01 – Updated: 2026-07-21 16:33
VLAI
EPSS
VEX
Title
PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334
Summary
PraisonAI is a multi-agent teams system. The v4.6.32 chokepoint refactor (which patched CVE-2026-44334 / GHSA-xcmw-grxf-wjhj) added the PRAISONAI_ALLOW_LOCAL_TOOLS env-var gate to the tool_override.py sinks. However, two additional spec.loader.exec_module call sites in praisonai/agents_generator.py were missed and remain completely unguarded in versions prior to 4.6.40. Both functions accept a module_path parameter sourced from YAML configuration and execute it without validation, signature checking, or the env-var gate. Version 4.6.40 fixes the issue.
Severity
8.1 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1685 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47398",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T16:33:17.988858Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:33:53.371Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-78r8-wwqv-r299"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. The v4.6.32 chokepoint refactor (which patched CVE-2026-44334 / GHSA-xcmw-grxf-wjhj) added the PRAISONAI_ALLOW_LOCAL_TOOLS env-var gate to the tool_override.py sinks. However, two additional spec.loader.exec_module call sites in praisonai/agents_generator.py were missed and remain completely unguarded in versions prior to 4.6.40. Both functions accept a module_path parameter sourced from YAML configuration and execute it without validation, signature checking, or the env-var gate. Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.1,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-829",
"description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:01:22.037Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-78r8-wwqv-r299",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-78r8-wwqv-r299"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1685",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1685"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619"
}
],
"source": {
"advisory": "GHSA-78r8-wwqv-r299",
"discovery": "UNKNOWN"
},
"title": "PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47398",
"datePublished": "2026-07-21T16:01:22.037Z",
"dateReserved": "2026-05-19T19:22:45.730Z",
"dateUpdated": "2026-07-21T16:33:53.371Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47397 (GCVE-0-2026-47397)
Vulnerability from cvelistv5 – Published: 2026-07-21 15:57 – Updated: 2026-07-23 14:25
VLAI
EPSS
VEX
Title
PraisonAI has an Arbitrary File Write in Python API
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. `write_file` skips path validation when `workspace=None` (always `None` in production). Version 4.6.40 fixes the issue.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47397",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-23T14:25:47.720177Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T14:25:50.782Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hvhp-v2gc-268q"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. `write_file` skips path validation when `workspace=None` (always `None` in production). Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 7.1,
"baseSeverity": "HIGH",
"privilegesRequired": "LOW",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:57:25.695Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hvhp-v2gc-268q",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hvhp-v2gc-268q"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-hvhp-v2gc-268q",
"discovery": "UNKNOWN"
},
"title": "PraisonAI has an Arbitrary File Write in Python API"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47397",
"datePublished": "2026-07-21T15:57:25.695Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-23T14:25:50.782Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47396 (GCVE-0-2026-47396)
Vulnerability from cvelistv5 – Published: 2026-07-21 15:55 – Updated: 2026-07-22 14:13
VLAI
EPSS
VEX
Title
PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token allows any reachable client to list agents, inspect agent metadata and instructions, invoke agents, and unregister agents. This is security-relevant because the bundled call server includes the vulnerable router and binds to `0.0.0.0`. As a result, operators who launch the call server without explicitly setting `CALL_SERVER_TOKEN` may unintentionally expose an unauthenticated remote agent control plane. Version 4.6.40 fixes the issue.
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47396",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:13:08.439122Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:13:42.099Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-86qc-r5v2-v6x6"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI\u0027s call server exposes a network-facing agent control API without authentication when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token allows any reachable client to list agents, inspect agent metadata and instructions, invoke agents, and unregister agents. This is security-relevant because the bundled call server includes the vulnerable router and binds to `0.0.0.0`. As a result, operators who launch the call server without explicitly setting `CALL_SERVER_TOKEN` may unintentionally expose an unauthenticated remote agent control plane. Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-284",
"description": "CWE-284: Improper Access Control",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:55:22.599Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-86qc-r5v2-v6x6",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-86qc-r5v2-v6x6"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619"
}
],
"source": {
"advisory": "GHSA-86qc-r5v2-v6x6",
"discovery": "UNKNOWN"
},
"title": "PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47396",
"datePublished": "2026-07-21T15:55:22.599Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-22T14:13:42.099Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47395 (GCVE-0-2026-47395)
Vulnerability from cvelistv5 – Published: 2026-07-21 15:52 – Updated: 2026-07-21 17:15
VLAI
EPSS
VEX
Title
PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.
Severity
5.5 (Medium)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
|
| MervinPraison | praisonaiagents |
Affected:
< 1.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47395",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T17:09:32.354388Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T17:15:13.196Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
},
{
"product": "praisonaiagents",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 1.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI\u0027s direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:\u003chttp-or-https-url\u003e`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator\u0027s machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 5.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-200",
"description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:52:52.682Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-5cxw-77wg-jrf3",
"discovery": "UNKNOWN"
},
"title": "PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47395",
"datePublished": "2026-07-21T15:52:52.682Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-21T17:15:13.196Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47394 (GCVE-0-2026-47394)
Vulnerability from cvelistv5 – Published: 2026-07-21 15:44 – Updated: 2026-07-21 18:01
VLAI
EPSS
VEX
Title
PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` ("fix(security): harden MCP rules path handling…") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pattern, `workflow.validate` and `deploy.validate`. Neither was mentioned in the original advisory. Both remained unchanged. The original advisory also identified the dispatcher (`server.py:281-298`) as a root cause. It accepts unvalidated `**kwargs` from `params["arguments"]` with no enforcement against the tool's declared `input_schema`. That code is unchanged prior to version 4.6.40. A single unauthenticated MCP `tools/call` to `praisonai.workflow.show` returns the contents of any file the host user can read: `/etc/passwd`, `~/.ssh/id_rsa`, `~/.aws/credentials`, or any project `.env`. Version 4.6.40 contains an updated fix.
Severity
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47394",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T18:00:46.506651Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T18:01:03.736Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9cr9-25q5-8prj"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` (\"fix(security): harden MCP rules path handling\u2026\") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pattern, `workflow.validate` and `deploy.validate`. Neither was mentioned in the original advisory. Both remained unchanged. The original advisory also identified the dispatcher (`server.py:281-298`) as a root cause. It accepts unvalidated `**kwargs` from `params[\"arguments\"]` with no enforcement against the tool\u0027s declared `input_schema`. That code is unchanged prior to version 4.6.40. A single unauthenticated MCP `tools/call` to `praisonai.workflow.show` returns the contents of any file the host user can read: `/etc/passwd`, `~/.ssh/id_rsa`, `~/.aws/credentials`, or any project `.env`. Version 4.6.40 contains an updated fix."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "NONE"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-200",
"description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:44:36.292Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9cr9-25q5-8prj",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9cr9-25q5-8prj"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-9cr9-25q5-8prj",
"discovery": "UNKNOWN"
},
"title": "PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47394",
"datePublished": "2026-07-21T15:44:36.292Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-21T18:01:03.736Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47393 (GCVE-0-2026-47393)
Vulnerability from cvelistv5 – Published: 2026-07-21 15:39 – Updated: 2026-07-22 14:34
VLAI
EPSS
VEX
Title
PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default
Summary
PraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_api_server_code`) that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart (`praisonai deploy --type api`) get a server that binds to `0.0.0.0` per the recommended sample YAML, exposes `/chat` and `/agents` endpoints, runs `praisonai.run()` on user-supplied JSON input — LLM orchestration with the API key materials present in the process environment, and does not require any authentication. Versions prior to 4.6.40 still ship the generator with `auth_enabled` defaulting to `False`. The fix shape is opt-in via `APIConfig(auth_enabled=True, auth_token=...)`. Version 4.6.40 fixes the issue.
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1685 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
| https://github.com/advisories/GHSA-6rmh-7xcm-cpxj | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47393",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:33:44.826949Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:34:05.072Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8444-4fhq-fxpq"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_api_server_code`) that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart (`praisonai deploy --type api`) get a server that binds to `0.0.0.0` per the recommended sample YAML, exposes `/chat` and `/agents` endpoints, runs `praisonai.run()` on user-supplied JSON input \u2014 LLM orchestration with the API key materials present in the process environment, and does not require any authentication. Versions prior to 4.6.40 still ship the generator with `auth_enabled` defaulting to `False`. The fix shape is opt-in via `APIConfig(auth_enabled=True, auth_token=...)`. Version 4.6.40 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-1188",
"description": "CWE-1188: Insecure Default Initialization of Resource",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:39:28.459Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8444-4fhq-fxpq",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8444-4fhq-fxpq"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1685",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1685"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/ef79b7a0561796ad9807f0f09538c25cc78d3619"
},
{
"name": "https://github.com/advisories/GHSA-6rmh-7xcm-cpxj",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/advisories/GHSA-6rmh-7xcm-cpxj"
}
],
"source": {
"advisory": "GHSA-8444-4fhq-fxpq",
"discovery": "UNKNOWN"
},
"title": "PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47393",
"datePublished": "2026-07-21T15:39:28.459Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-22T14:34:05.072Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47392 (GCVE-0-2026-47392)
Vulnerability from cvelistv5 – Published: 2026-07-21 15:27 – Updated: 2026-07-21 16:39
VLAI
EPSS
VEX
Title
PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. This is a novel bypass that survives all patches for CVE-2026-39888 (frame traversal), CVE-2026-34938 (str subclass), and CVE-2026-40158 (`type.__getattribute__` trampoline). PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain an updated fix.
Severity
9.9 (Critical)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
|
| MervinPraison | < 1.6.40 |
Affected:
praisonaiagents
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47392",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-21T16:39:00.607801Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:39:40.246Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
},
{
"product": "\u003c 1.6.40",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "praisonaiagents"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. This is a novel bypass that survives all patches for CVE-2026-39888 (frame traversal), CVE-2026-34938 (str subclass), and CVE-2026-40158 (`type.__getattribute__` trampoline). PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain an updated fix."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.9,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-184",
"description": "CWE-184: Incomplete List of Disallowed Inputs",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-693",
"description": "CWE-693: Protection Mechanism Failure",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:52:22.329Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-4mr5-g6f9-cfrh",
"discovery": "UNKNOWN"
},
"title": "PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47392",
"datePublished": "2026-07-21T15:27:16.557Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-21T16:39:40.246Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47391 (GCVE-0-2026-47391)
Vulnerability from cvelistv5 – Published: 2026-07-21 15:21 – Updated: 2026-07-23 14:27
VLAI
EPSS
VEX
Title
PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue.
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1793 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47391",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-23T14:27:02.928342Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T14:27:07.049Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI\u0027s first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-95",
"description": "CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T15:21:22.916Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1793",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1793"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747"
}
],
"source": {
"advisory": "GHSA-vg22-4gmj-prxw",
"discovery": "UNKNOWN"
},
"title": "PraisonAI\u0027s unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47391",
"datePublished": "2026-07-21T15:21:22.916Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-23T14:27:07.049Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-47390 (GCVE-0-2026-47390)
Vulnerability from cvelistv5 – Published: 2026-07-21 14:47 – Updated: 2026-07-22 14:10
VLAI
EPSS
VEX
Title
PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings
Summary
PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `spider_tools` URL validation can be bypassed using alternate loopback host encodings. The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled URLs. However, the validation only blocks a small set of exact host strings such as `localhost` and `127.0.0.1`. It does not normalize hostnames, resolve DNS, parse numeric IPv4 variants, or validate the final resolved IP address before making the request. As a result, certain URLs may bypass the protection and still reach loopback services. After the weak validation passes, `scrape_page()` calls `requests.Session.get()` on the attacker-controlled URL. This allows an attacker who can influence URLs passed to `scrape_page`, `crawl`, or `extract_text` to induce SSRF requests against loopback-only services. This is a server-side request forgery protection bypass. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a patch.
Severity
5.5 (Medium)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/MervinPraison/PraisonAI/securi… | x_refsource_CONFIRM |
| https://github.com/MervinPraison/PraisonAI/pull/1684 | x_refsource_MISC |
| https://github.com/MervinPraison/PraisonAI/commit… | x_refsource_MISC |
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| MervinPraison | PraisonAI |
Affected:
< 4.6.40
|
|
| MervinPraison | praisonaiagents |
Affected:
< 1.6.40
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-47390",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T14:08:40.990468Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T14:10:08.532Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5c6w-wwfq-7qqm"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "PraisonAI",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 4.6.40"
}
]
},
{
"product": "praisonaiagents",
"vendor": "MervinPraison",
"versions": [
{
"status": "affected",
"version": "\u003c 1.6.40"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `spider_tools` URL validation can be bypassed using alternate loopback host encodings. The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled URLs. However, the validation only blocks a small set of exact host strings such as `localhost` and `127.0.0.1`. It does not normalize hostnames, resolve DNS, parse numeric IPv4 variants, or validate the final resolved IP address before making the request. As a result, certain URLs may bypass the protection and still reach loopback services. After the weak validation passes, `scrape_page()` calls `requests.Session.get()` on the attacker-controlled URL. This allows an attacker who can influence URLs passed to `scrape_page`, `crawl`, or `extract_text` to induce SSRF requests against loopback-only services. This is a server-side request forgery protection bypass. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a patch."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 5.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T14:47:53.059Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5c6w-wwfq-7qqm",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5c6w-wwfq-7qqm"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/pull/1684",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/pull/1684"
},
{
"name": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6"
}
],
"source": {
"advisory": "GHSA-5c6w-wwfq-7qqm",
"discovery": "UNKNOWN"
},
"title": "PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-47390",
"datePublished": "2026-07-21T14:47:53.059Z",
"dateReserved": "2026-05-19T19:22:45.729Z",
"dateUpdated": "2026-07-22T14:10:08.532Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}