CVE-2026-61447
PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets
Severidad por fuente
La etiqueta propia de Trivy es CRITICAL. Crítica según GHSA.
Descripción
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.
Paquetes afectados y versiones corregidas
| Fuente | Paquete | Corregido en |
|---|---|---|
| pip::GitHub Security Advisory pip | praisonaiagents | 1.6.78 |