CVEvulnerability

CVE-2026-40088

9.6 CRITICAL Published 2026-04-09 Modified 2026-10-25 Official page ↗
Status
Analyzed
Published
2026-04-09
Last modified
2026-10-25
Assigner
[email protected]
CVSS 3.1 ([email protected])
9.6 CRITICAL — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
CVSS 3.1 ([email protected])
9.6 CRITICAL — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
Weaknesses
CWE-78

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.

Affected configurations

• praison praisonai (< 4.5.121)

Related

Weakness · CWE (1)

  • CWE-78 Improper Neutralization of Special Elements used in an OS Command weakness

References