CVE-2026-40088

moderate-risk
Published 2026-04-09

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.

Do I need to act?

-
0.05% chance of exploitation
EPSS score — low exploit probability
-
Not on CISA KEV list
No confirmed active exploitation reported to CISA
?
Patch status unknown
Check vendor advisories for fix availability and mitigation guidance
9
CVSS 9.6/10 Critical
NETWORK / LOW complexity

Affected Products (1)

Affected Vendors

Praison

References (2)

Release Notes https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121
Exploit https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c7...
37
/ 100
moderate-risk
Severity 32/34 · Critical
Exploitability 0/34 · Minimal
Exposure 5/34 · Minimal