CVE-2026-57125
PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass
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.
INFO
Published Date :
Sept. 14, 2026, 2:19 p.m.
Last Modified :
Sept. 14, 2026, 2:19 p.m.
Remotely Exploit :
No
Source :
GitHub_M
Affected Products
The following products are affected by CVE-2026-57125
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
Solution
- Update PraisonAI to 4.6.59.
- Update PraisonAI Agents to 1.6.59.
- Verify update deployment.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-57125 vulnerability anywhere in the article.