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.
Project Subscriptions
No data.
Advisories
| Source | ID | Title |
|---|---|---|
Github GHSA |
GHSA-2763-cj5r-c79m | PraisonAI Vulnerable to OS Command Injection |
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Thu, 09 Apr 2026 20:00:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in praisonai | |
| Weaknesses | CWE-78 | |
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-04-09T20:14:56.938Z
Reserved: 2026-04-09T00:39:12.206Z
Link: CVE-2026-40088
No data.
Status : Received
Published: 2026-04-09T20:16:27.597
Modified: 2026-04-09T20:16:27.597
Link: CVE-2026-40088
No data.
OpenCVE Enrichment
No data.
Weaknesses
Github GHSA