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.
Affected products
praison: praisonai
References3
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qh… ExploitMitigationPatchVendor Advisory
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qh… ExploitMitigationPatchVendor Advisory
- github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf6… Patch
Metrics
- CVSS 3.1
-
9.8
CRITICAL
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - EPSS — exploit probability
- 1% percentile: 46 · as of 13 November 2026
- CWE
- CWE-77CWE-78
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.