Vulnerability Description
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @require_approval checks critical tools. This chain allows a remote caller to cause a configured language model agent to invoke arbitrary operating-system commands without credentials or operator interaction. This vulnerability is fixed in praisonai 4.6.59 and praisonaiagents 1.6.59 as fixed versions.
CVSS Score
CRITICAL
Related Weaknesses (CWE)
References
- https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q2
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q2
FAQ
What is CVE-2026-57125?
CVE-2026-57125 is a vulnerability with a CVSS score of 9.8 (CRITICAL). PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve fi...
How severe is CVE-2026-57125?
CVE-2026-57125 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-2026-57125?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.