alterlab-scgpt

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill demonstrates a clear and legitimate purpose for academic research in genomics, specifically for single-cell data processing.
  • [EXTERNAL_DOWNLOADS]: The skill references downloading pretrained checkpoints from the 'bowang-lab/scGPT' repository. This is a standard and necessary component for the functionality of the scGPT foundation model.
  • [COMMAND_EXECUTION]: Execution of Python scripts via the 'uv' package manager is intended for scientific data analysis on AnnData files, consistent with the tool's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 11:25 PM
Security Audit — agent-trust-hub — alterlab-scgpt