CVE-2026-40088

Description

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121.

CVSS Vector

References

• https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121
• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79m