CVE-2026-57125
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.
Schwachstellenklasse
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.
Quellen
- 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
Finden Sie die Schwachstelle, bevor es ein Angreifer tut.
Melden Sie sich mit GitHub an und starten Sie Ihr erstes Audit in weniger als einer Minute. Für den kostenlosen Plan ist keine Kreditkarte nötig.