CVE-2026-56075: PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVA...

Added to the CISA Known Exploited Vulnerabilities catalog on 18 Jun 2026. Vendor: AI/ML. Product: LLM. CVSS score: 8.8.

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

Required action: Review and patch if applicable to your AI infrastructure.