LLMHigh
CVE-2026-61447: PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python(…
- Occurred
- Jul 11, 2026
- Published
- Jul 11, 2026
- Source
- NVD CVE
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.
Tags
- CVE
- CVE-2026-61447
- cvss:CRITICAL
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Remote code execution vulnerability in LLM-generated code execution without proper sandboxing allows arbitrary code execution and data exfiltration.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8