CVE-2026-41497
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…
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.54%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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 3.1
- 9.8 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.54% probability · 44th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-77, CWE-78
- Affected
- praison/praisonai
- Source
- security-advisories@github.com
References
- https://github.com/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368cPatch
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3jExploit, Mitigation, Patch, Vendor Advisory
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9qhq-v63v-fv3jExploit, Mitigation, Patch, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.