# CVE-2026-57125

## Summary

- **CVE ID:** CVE-2026-57125
- **Severity:** CRITICAL
- **CVSS Score:** 9.8 (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H)
- **CWE:** CWE-306, CWE-863
- **Published:** Sep 14, 2026
- **Last Modified:** Sep 14, 2026

## 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.

## Affected Products

- MervinPraison — PraisonAI (< 4.6.59)
- MervinPraison — praisonaiagents (< 1.6.59)

## References

- [CNA](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x)
- [CNA](https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9)
- [CNA](https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.41%
- **EPSS Percentile:** 35.0

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-17._