VULNERABILITY INTELLIGENCE
CVE-2026-61447
CVSS score10 CRITICAL
EPSS probability15.24%
CISA KEVNot currently listed
Published2026-07-11
Last modified2026-10-25
CVSS vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Description
PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.
Weakness classification
- disclosure@vulncheck.com: CWE-94