torchdrug
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): Technical documentation analysis shows no evidence of prompt injection, obfuscation, or malicious intent.
- [DATA_EXPOSURE] (SAFE): Code snippets utilize local filesystem paths (e.g., '
/kg-datasets/', '/molecule-datasets/') for loading datasets and model weights, which is a standard and safe practice for local model development. - [EXTERNAL_DOWNLOADS] (SAFE): No scripts or commands for downloading untrusted third-party executables or remote scripts were identified. The use of standard ML libraries like 'torch' and 'torchdrug' is consistent with the stated purpose of the skill.
Audit Metadata