GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

CVE-2026-34935 (GCVE-0-2026-34935)

Vulnerability from cvelistv5 – Published: 2026-04-03 22:48 – Updated: 2026-04-06 19:04
VLAI
Title
PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()
Summary
PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.
Severity
9.8 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
SSVC
Exploitation: poc Automatable: yes Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-04-06 19:04 UTC
CWE
  • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Assigner
References
Impacted products
Vendor Product Version CPE status
MervinPraison PraisonAI Affected: >= 4.5.15, < 4.5.69
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-34935",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-04-06T19:04:17.102835Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-04-06T19:04:26.478Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "PraisonAI",
          "vendor": "MervinPraison",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 4.5.15, \u003c 4.5.69"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69."
        }
      ],
      "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-78",
              "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-04-03T22:48:21.261Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m"
        },
        {
          "name": "https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c"
        }
      ],
      "source": {
        "advisory": "GHSA-9gm9-c8mq-vq7m",
        "discovery": "UNKNOWN"
      },
      "title": "PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-34935",
    "datePublished": "2026-04-03T22:48:21.261Z",
    "dateReserved": "2026-03-31T17:27:08.660Z",
    "dateUpdated": "2026-04-06T19:04:26.478Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-34935",
      "date": "2026-09-15",
      "epss": "0.00824",
      "percentile": "0.55418"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-34935\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-04-03T23:17:05.693\",\"lastModified\":\"2026-07-24T22:10:00.140\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.\"},{\"lang\":\"es\",\"value\":\"PraisonAI es un sistema de equipos multiagente. Desde la versi\u00f3n 4.5.15 hasta antes de la versi\u00f3n 4.5.69, el argumento CLI --mcp se pasa directamente a shlex.split() y se reenv\u00eda a trav\u00e9s de la cadena de llamadas a anyio.open_process() sin validaci\u00f3n, verificaci\u00f3n de lista blanca o saneamiento en ning\u00fan salto, lo que permite la ejecuci\u00f3n arbitraria de comandos del sistema operativo como el usuario del proceso. Este problema ha sido parcheado en la versi\u00f3n 4.5.69.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"MervinPraison\",\"product\":\"PraisonAI\",\"versions\":[{\"version\":\"\u003e= 4.5.15, \u003c 4.5.69\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":9.8,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":5.9}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-04-06T19:04:17.102835Z\",\"id\":\"CVE-2026-34935\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"yes\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-78\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*\",\"versionStartIncluding\":\"4.5.15\",\"versionEndExcluding\":\"4.5.69\",\"matchCriteriaId\":\"5FE53D99-2CEE-4ECB-A45E-8F0E5A5A2878\"}]}]}],\"references\":[{\"url\":\"https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\"]},{\"url\":\"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Vendor Advisory\"]}]}}",
    "redhat_vex": {
      "current_release_date": "2026-04-06T10:57:12+00:00",
      "cve": "CVE-2026-34935",
      "id": "CVE-2026-34935",
      "initial_release_date": "2026-01-01T00:00:00+00:00",
      "product_status:known_not_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34935.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": "{\"cna\": {\"title\": \"PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()\", \"problemTypes\": [{\"descriptions\": [{\"cweId\": \"CWE-78\", \"lang\": \"en\", \"description\": \"CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)\", \"type\": \"CWE\"}]}], \"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\"}}], \"references\": [{\"name\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m\", \"tags\": [\"x_refsource_CONFIRM\"], \"url\": \"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m\"}, {\"name\": \"https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c\", \"tags\": [\"x_refsource_MISC\"], \"url\": \"https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c\"}], \"affected\": [{\"vendor\": \"MervinPraison\", \"product\": \"PraisonAI\", \"versions\": [{\"version\": \"\u003e= 4.5.15, \u003c 4.5.69\", \"status\": \"affected\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-04-03T22:48:21.261Z\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.\"}], \"source\": {\"advisory\": \"GHSA-9gm9-c8mq-vq7m\", \"discovery\": \"UNKNOWN\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-34935\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-04-06T19:04:17.102835Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-04-06T19:04:22.554Z\"}}]}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-34935\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"state\": \"PUBLISHED\", \"assignerShortName\": \"GitHub_M\", \"dateReserved\": \"2026-03-31T17:27:08.660Z\", \"datePublished\": \"2026-04-03T22:48:21.261Z\", \"dateUpdated\": \"2026-04-06T19:04:26.478Z\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





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.


Detection rules are retrieved from Rulezet.


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.