CVE-2026-40088

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121.

CVSS v3 9.6 CRITICAL

9.6^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 2.8 / Impact : 6.0

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope CHANGED

References

Link	Resource
https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121	Release Notes
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79m	Exploit Vendor Advisory

Configurations

Configuration 1 (hide)

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

History

25 Oct 2026, 23:10

Type	Values Removed	Values Added
Summary		(es) PraisonAI es un sistema de equipos multiagente. Antes de 4.5.121, la función execute_command y la ejecución de shell de flujo de trabajo están expuestas a entrada controlada por el usuario a través de flujos de trabajo de agente, definiciones YAML y llamadas a herramientas generadas por LLM, permitiendo a los atacantes inyectar comandos de shell arbitrarios a través de metacaracteres de shell. Esta vulnerabilidad está corregida en 4.5.121.

Information

Published : 2026-04-09 20:16

Updated : 2026-10-25 23:10

NVD link : CVE-2026-40088

Mitre link : CVE-2026-40088

CVE.ORG link : CVE-2026-40088

JSON object : View

Products Affected

praison

praisonai

CWE

CWE-78

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

{"id": "CVE-2026-40088", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-40088", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-04-09T20:14:27.344510Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 9.6, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 2.8}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 9.6, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 2.8}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "MervinPraison", "product": "PraisonAI", "versions": [{"status": "affected", "version": "< 4.5.121"}]}]}], "published": "2026-04-09T20:16:27.597", "references": [{"url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121", "tags": ["Release Notes"], "source": "security-advisories@github.com"}, {"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79m", "tags": ["Exploit", "Vendor Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-78"}]}], "descriptions": [{"lang": "en", "value": "PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121."}, {"lang": "es", "value": "PraisonAI es un sistema de equipos multiagente. Antes de 4.5.121, la funci\u00f3n execute_command y la ejecuci\u00f3n de shell de flujo de trabajo est\u00e1n expuestas a entrada controlada por el usuario a trav\u00e9s de flujos de trabajo de agente, definiciones YAML y llamadas a herramientas generadas por LLM, permitiendo a los atacantes inyectar comandos de shell arbitrarios a trav\u00e9s de metacaracteres de shell. Esta vulnerabilidad est\u00e1 corregida en 4.5.121."}], "lastModified": "2026-10-25T23:10:00.167", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "80F7B2D9-522C-4112-BE9F-DA0C4D9FE908", "versionEndExcluding": "4.5.121"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}