mllm-eval
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a Python script (check_mllm_eval_completeness.py) for static analysis of evaluation plans. This script exclusively uses the Python standard library and performs no network operations or dynamic code execution.
- [SAFE]: No hardcoded credentials or sensitive file paths were detected. The skill is designed for advisory use in clinical evaluation design.
- [SAFE]: No prompt injection or obfuscation techniques were identified. The instructions focus on scientific auditing and reporting standards (TRIPOD-LLM, MI-CLEAR-LLM).
- [SAFE]: The provided scripts and tests follow safe coding practices, such as using json.loads with constant rejection to prevent specific JSON-related exploits.
Audit Metadata