skills/crazymsn/academic-skills/pytdc/Gen Agent Trust Hub

pytdc

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill integrates the PyTDC library, which is a reputable resource for therapeutic machine learning developed by the Mims Lab at Harvard University. The installation instructions use uv pip, a standard modern Python package manager.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of AI-ready biomedical datasets from the official Therapeutics Data Commons infrastructure. These downloads are intrinsic to the skill's stated purpose of providing drug discovery data for benchmarking and research.
  • [COMMAND_EXECUTION]: The provided Python templates in the scripts/ directory demonstrate standard data science workflows using pandas and numpy. No evidence was found of unsafe subprocess calls, privilege escalation, or persistence mechanisms.
  • [PROMPT_INJECTION]: The documentation and instructions are strictly technical and instructional, with no attempts to override agent behavior or bypass safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:23 AM
Security Audit — agent-trust-hub — pytdc