Vulnerability · Published Sep 14, 2026 · Assigned by GitHub_M

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

Critical 9.8

In plain English

A critical-severity missing authentication in PraisonAI from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 49% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)9.8Critical

Exploit odds (30 days)0.6%top 51.1% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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 packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	praisonai	4.6.59	GHSA-4869-x4pr-q22x
PyPI	praisonai	4.6.59	PYSEC-2026-3501
PyPI	praisonaiagents	1.6.59	GHSA-4869-x4pr-q22x
PyPI	praisonaiagents	1.6.59	PYSEC-2026-3529

Affected products (as reported)

Vendor	Product	Versions
MervinPraison	PraisonAI	< 4.6.59
MervinPraison	praisonaiagents	< 1.6.59

Weakness: CWE-306, CWE-863 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

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