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.
Metrics
CVSS 3.1 9.6/10
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | PraisonAI | < 4.5.121 |
References
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121Release Notes
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79mExploit, Vendor Advisory
Timeline
- Published
- Apr 9, 2026
- Last modified
- Oct 25, 2026
- NVD status
- Analyzed