single-cell-foundation-model-stofm

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to interact with a specific local repository at /DATA/disk0/zhaosy/home/SToFM for scientific data processing.
  • [SAFE]: All listed dependencies are legitimate scientific and machine learning packages (e.g., torch, scanpy, transformers) with pinned versions.
  • [SAFE]: External checkpoints and configuration files are handled securely by requiring the user to provide valid paths if assets are not found locally.
  • [SAFE]: References to external sources, such as the official GitHub repository and arXiv paper, are consistent with the skill's stated purpose and author.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 06:02 AM