CVE-2026-41497

PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parse_mcp_command(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. This issue has been patched in version 4.6.9.

CVSS v3 9.8 CRITICAL

9.8^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 3.9 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c	Patch
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j	Exploit Mitigation Patch Vendor Advisory
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j	Exploit Mitigation Patch Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*

History

26 Oct 2026, 19:10

Type	Values Removed	Values Added
Summary		(es) PraisonAI es un sistema de equipos multiagente. Antes de la versión 4.6.9, la corrección para el manejo de comandos MCP de PraisonAI no añade una lista blanca de comandos o validación de argumentos a parse_mcp_command(), permitiendo que ejecutables arbitrarios como bash, python o /bin/sh con indicadores de ejecución de código en línea pasen a la ejecución de subprocesos. Este problema ha sido parcheado en la versión 4.6.9.

Information

Published : 2026-05-08 14:16

Updated : 2026-10-26 19:10

NVD link : CVE-2026-41497

Mitre link : CVE-2026-41497

CVE.ORG link : CVE-2026-41497

JSON object : View

Products Affected

praison

praisonai

CWE

CWE-77

Improper Neutralization of Special Elements used in a Command ('Command Injection')

CWE-78

Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

{"id": "CVE-2026-41497", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-41497", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "yes"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-05-08T14:47:18.973445Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "MervinPraison", "product": "PraisonAI", "versions": [{"status": "affected", "version": "< 4.6.9"}]}]}], "published": "2026-05-08T14:16:33.843", "references": [{"url": "https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c", "tags": ["Patch"], "source": "security-advisories@github.com"}, {"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j", "tags": ["Exploit", "Mitigation", "Patch", "Vendor Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3j", "tags": ["Exploit", "Mitigation", "Patch", "Vendor Advisory"], "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-77"}, {"lang": "en", "value": "CWE-78"}]}], "descriptions": [{"lang": "en", "value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parse_mcp_command(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. This issue has been patched in version 4.6.9."}, {"lang": "es", "value": "PraisonAI es un sistema de equipos multiagente. Antes de la versi\u00f3n 4.6.9, la correcci\u00f3n para el manejo de comandos MCP de PraisonAI no a\u00f1ade una lista blanca de comandos o validaci\u00f3n de argumentos a parse_mcp_command(), permitiendo que ejecutables arbitrarios como bash, python o /bin/sh con indicadores de ejecuci\u00f3n de c\u00f3digo en l\u00ednea pasen a la ejecuci\u00f3n de subprocesos. Este problema ha sido parcheado en la versi\u00f3n 4.6.9."}], "lastModified": "2026-10-26T19:10:00.163", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "926F2340-8373-45E8-8F68-EDB9E771A52E", "versionEndExcluding": "4.6.9"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}