tao-mine-od-images
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The configuration validation script uses yaml.safe_load() for secure parsing of experiment specifications and performs existence checks on input paths.
- [SAFE]: The skill facilitates the use of official NVIDIA TAO toolkit container images from a trusted registry (nvcr.io).
- [SAFE]: The skill operates on local datasets (Parquet and JSON) without initiating unauthorized network connections or sensitive data access.
Audit Metadata