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.
Fix
Patch, vendor advisory and mitigation references on NVD 3
- 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
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 9.8 · praisonNVD modified 2026-10-26 19:10
Affected (CPE criteria) 1
cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*
References 3
- 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