Vulnerability Description
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 Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Praison | Praisonai | < 4.6.9 |
Related Weaknesses (CWE)
References
- https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4ePatch
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fvExploitVendor AdvisoryPatch
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fvExploitVendor AdvisoryPatch
FAQ
What is CVE-2026-41497?
CVE-2026-41497 is a vulnerability with a CVSS score of 9.8 (CRITICAL). 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 a...
How severe is CVE-2026-41497?
CVE-2026-41497 has been rated CRITICAL with a CVSS base score of 9.8/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-41497?
Check the references section above for vendor advisories and patch information. Affected products include: Praison Praisonai.