CVE-2026-61447

Summary

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.

Affected Software

VendorProductVersion RangeStatus
MervinPraisonPraisonAI0 < 1.6.78affected
MervinPraisonPraisonAI1.6.78unaffected

Weaknesses

  • CWE-94: Improper Control of Generation of Code ('Code Injection')

References