deepchem

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a technical guide for the DeepChem library. All code examples and instructions align with standard practices for molecular machine learning and data science.
  • [EXTERNAL_DOWNLOADS]: The skill references the auto-downloading of MoleculeNet benchmark datasets through dc.molnet.load_* functions. These are well-known, established scientific datasets used for benchmarking molecular models.
  • [COMMAND_EXECUTION]: Instructions include standard package installation via pip install for deepchem and its common backend dependencies like PyTorch and TensorFlow.
  • [DATA_EXFILTRATION]: No suspicious network operations or unauthorized sensitive file access patterns were detected. Data handling is limited to local CSV/SDF files and reputable scientific repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:35 PM
Security Audit — agent-trust-hub — deepchem