ml-mlip-speed
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The benchmarking script performs scientific calculations using ASE and PyTorch. It does not execute arbitrary or untrusted shell commands.
- [SAFE]: Data processing of YAML files uses
yaml.safe_load, which is a secure practice to prevent arbitrary code execution during deserialization. - [SAFE]: Dynamic imports are restricted to known local paths within the project structure to handle different model providers.
- [SAFE]: No network access or data exfiltration patterns were identified; the skill only writes result data and plots to the local file system as directed by user arguments.
Audit Metadata