What’s Vulnerable › Vulnerabilities

CVE-2026-57125: PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

• Severity: critical (CVSS 9.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.6% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-09-14 · updated 2026-09-15
• Weakness: CWE-306

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: before 4.6.59
• MervinPraison praisonaiagents: before 1.6.59

References

• https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9
• https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59
• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x
• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x

Get alerted when CVE-2026-57125 or the next vulnerability affects your stack