torchdrug

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides high-quality documentation and Python code templates for using the legitimate 'torchdrug' library in scientific contexts. It covers a wide range of drug discovery and biological modeling tasks without introducing any security risks.
  • [EXTERNAL_DOWNLOADS]: The skill mentions the installation of the 'torchdrug' package via 'uv pip install torchdrug'. This is a standard dependency installation for a well-known open-source library in the AI for science community.
  • [DATA_INGESTION]: While the skill describes workflows that ingest external scientific data (such as SMILES strings for molecules and PDB files for proteins), these are standard operations for the intended use-case of drug discovery and structural biology. No unsafe processing patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 08:21 AM
Security Audit — agent-trust-hub — torchdrug