CVE-2026-57125 in PraisonAIinfo

Zusammenfassung

von MITRE • 14.09.2026

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.

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Zuständig

GitHub M

Reservieren

24.06.2026

Veröffentlichung

14.09.2026

Moderieren

akzeptiert

Eintrag

VDB-403559

CPE

bereit

EPSS

0.00000

KEV

nein

Aktivitäten

very low

Quellen

Might our Artificial Intelligence support you?

Check our Alexa App!