CVE-2026-40088
Critical
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.
SeverityCritical
CVSS9.6
Exploit probability—
ProductPraisonai
PublishedApr 9, 2026
First seenApr 9, 2026
Weakness typeCWE-78OS command injection
How to fix
Update
- praison praisonai4.5.121 or later
- praisonai4.5.121 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| praison praisonai | v < 4.5.121 | 4.5.121 |
| praisonaiPyPI | v < 4.5.121 | 4.5.121 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.