9.8Critical

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

MervinPraison PraisonAI; MervinPraison praisonaiagents Published: (2 months ago)

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.

Weakness (CWE): CWE-306CWE-863

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
MervinPraison PraisonAI < 4.6.59
MervinPraison praisonaiagents < 1.6.59

References and patches