CVE-2026-65699 (GCVE-0-2026-65699)
Vulnerability from cvelistv5 – Published: 2026-07-23 16:59 – Updated: 2026-07-23 18:17 X_Open Source Unsupported When Assigned
VLAI
EPSS
VEX
Title
AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation
Summary
AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target run_id in the request body without ownership verification. The AgentCRUD.create_task and validate_task_count functions look up the target AgentRun using the client-supplied run_id without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid run_id to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim's run.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-23 18:17 UTC
CWE
- CWE-639 - Authorization Bypass Through User-Controlled Key
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/geo-chen/oss/blob/main/AgentGPT.md | technical-descriptionexploit |
| https://www.vulncheck.com/advisories/agentgpt-aut… | third-party-advisory |
Impacted products
Date Public
2026-07-17 00:00
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-65699",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-23T18:17:18.104555Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T18:17:32.104Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "affected",
"packageURL": "pkg:github/reworkd/AgentGPT",
"product": "AgentGPT",
"repo": "https://github.com/reworkd/AgentGPT",
"vendor": "reworkd",
"versions": [
{
"lessThanOrEqual": "1.0.0",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "George Chen"
}
],
"datePublic": "2026-07-17T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user\u0027s agent run by supplying a target run_id in the request body without ownership verification. The AgentCRUD.create_task and validate_task_count functions look up the target AgentRun using the client-supplied run_id without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid run_id to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim\u0027s run."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 2.3,
"baseSeverity": "LOW",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "LOW",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "LOW",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 4.2,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-639",
"description": "Authorization Bypass Through User-Controlled Key",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T16:59:46.107Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Researcher Disclosure",
"tags": [
"technical-description",
"exploit"
],
"url": "https://github.com/geo-chen/oss/blob/main/AgentGPT.md"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/agentgpt-authorization-bypass-via-agent-task-creation"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source",
"unsupported-when-assigned"
],
"title": "AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-65699",
"datePublished": "2026-07-23T16:59:46.107Z",
"dateReserved": "2026-07-22T20:26:09.980Z",
"dateUpdated": "2026-07-23T18:17:32.104Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-65699",
"date": "2026-10-28",
"epss": "0.00276",
"percentile": "0.19962"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "affected",
"packageURL": "pkg:github/reworkd/AgentGPT",
"product": "AgentGPT",
"repo": "https://github.com/reworkd/AgentGPT",
"vendor": "reworkd",
"versions": [
{
"lessThanOrEqual": "1.0.0",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"cveTags": [
{
"sourceIdentifier": "disclosure@vulncheck.com",
"tags": [
"unsupported-when-assigned"
]
}
],
"descriptions": [
{
"lang": "en",
"value": "AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user\u0027s agent run by supplying a target run_id in the request body without ownership verification. The AgentCRUD.create_task and validate_task_count functions look up the target AgentRun using the client-supplied run_id without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid run_id to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim\u0027s run."
},
{
"lang": "es",
"value": "AgentGPT hasta la 1.0.0 contiene una omisi\u00f3n de autorizaci\u00f3n a trav\u00e9s de una vulnerabilidad de clave controlada por el usuario que permite a los usuarios autenticados adjuntar tareas a la ejecuci\u00f3n de un agente de otro usuario al proporcionar un run_id objetivo en el cuerpo de la solicitud sin verificaci\u00f3n de propiedad. Las funciones AgentCRUD.create_task y validate_task_count buscan el AgentRun objetivo utilizando el run_id proporcionado por el cliente sin confirmar que la ejecuci\u00f3n pertenece al usuario solicitante, lo que permite a un atacante que obtiene un run_id v\u00e1lido corromper el historial de tareas, agotar el presupuesto de bucle por ejecuci\u00f3n y generar costos de LLM contra la ejecuci\u00f3n de la v\u00edctima."
}
],
"id": "CVE-2026-65699",
"lastModified": "2026-10-24T13:10:00.147",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 4.2,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L",
"version": "3.1"
},
"exploitabilityScore": 1.6,
"impactScore": 2.5,
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 2.3,
"baseSeverity": "LOW",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"version": "4.0",
"vulnAvailabilityImpact": "LOW",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "LOW",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-65699",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-23T18:17:18.104555Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-07-23T18:17:01.153",
"references": [
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/geo-chen/oss/blob/main/AgentGPT.md"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.vulncheck.com/advisories/agentgpt-authorization-bypass-via-agent-task-creation"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Deferred",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-639"
}
],
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-65699",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-23T18:17:18.104555Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T18:17:23.390Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "affected",
"packageURL": "pkg:github/reworkd/AgentGPT",
"product": "AgentGPT",
"repo": "https://github.com/reworkd/AgentGPT",
"vendor": "reworkd",
"versions": [
{
"lessThanOrEqual": "1.0.0",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "George Chen"
}
],
"datePublic": "2026-07-17T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user\u0027s agent run by supplying a target run_id in the request body without ownership verification. The AgentCRUD.create_task and validate_task_count functions look up the target AgentRun using the client-supplied run_id without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid run_id to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim\u0027s run."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 2.3,
"baseSeverity": "LOW",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "LOW",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "LOW",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 4.2,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-639",
"description": "Authorization Bypass Through User-Controlled Key",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-23T16:59:46.107Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Researcher Disclosure",
"tags": [
"technical-description",
"exploit"
],
"url": "https://github.com/geo-chen/oss/blob/main/AgentGPT.md"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/agentgpt-authorization-bypass-via-agent-task-creation"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source",
"unsupported-when-assigned"
],
"title": "AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-65699",
"datePublished": "2026-07-23T16:59:46.107Z",
"dateReserved": "2026-07-22T20:26:09.980Z",
"dateUpdated": "2026-07-23T18:17:32.104Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
How durations are calculated
Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.
Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.
Loading timeline…
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.