anndata

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill follows established best practices for data science and genomics analysis, focusing exclusively on the legitimate use of the anndata library.
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of the anndata package from standard Python package registries via uv pip install. It also references official documentation from the scverse organization (anndata, scanpy), which are well-known and trusted entities in the scientific community.
  • [DATA_EXFILTRATION]: While the documentation demonstrates reading data from external URLs (e.g., Zarr stores on S3 or H5AD files via HTTPS), these are standard operations for accessing public scientific datasets and do not involve the collection or transmission of sensitive local data or credentials.
  • [COMMAND_EXECUTION]: No suspicious shell command execution was found. The skill uses standard CLI tools (uv) for package management and includes common bioinformatics preprocessing commands that are benign in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 03:41 PM
Security Audit — agent-trust-hub — anndata