RCE in Mervinpraison Praisonai
CVE-2026-40088
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.
Vulnerability class: Command Injection (OS Command Injection)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.6 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.004, 37.4th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Mervinpraison Praisonai — versions < 4.5.121
- Praison Praisonai
Weakness classification (CWE)
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79m (Exploit, Vendor Advisory)
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121 (Release Notes)