CVE-2026-40088 | THREATINT

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.

PUBLISHED Reserved 2026-04-09 | Published 2026-04-09 | Updated 2026-04-09 | Assigner GitHub_M

CRITICAL: 9.7CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Problem types

CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

Product status

< 4.5.121

affected

References

github.com/...isonAI/security/advisories/GHSA-2763-cj5r-c79m

github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121

cve.org (CVE-2026-40088)

nvd.nist.gov (CVE-2026-40088)

Download JSON