Vulnerability Description
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xq
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xq
FAQ
What is CVE-2026-57137?
CVE-2026-57137 is a vulnerability with a CVSS score of 8.8 (HIGH). PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall app...
How severe is CVE-2026-57137?
CVE-2026-57137 has been rated HIGH with a CVSS base score of 8.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-57137?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.