9.7
/ 10
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
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.
AI Analysis
OS Command Injection vulnerability in PraisonAI due to improper neutralization of special elements used in an OS command, allowing attackers to inject arbitrary shell commands.
Basic Information
ID
CVE-2026-40088
Source
GitHub_M
Published
Apr 9, 2026 at 19:45
Modified
Apr 9, 2026 at 20:14
Affected Product
Vendor
MervinPraison
Product
PraisonAI
Version
< 4.5.121
Affected Versions
MervinPraison PraisonAI < 4.5.121
CWE Classification
AI Assessment
AI Score
9.7 / 10
AI Severity
Critical
Vendor
MervinPraison
Product
PraisonAI
Version
< 4.5.121