NYC
skills/ovachiever/droid-tings/scanpy/Gen Agent Trust Hub

scanpy

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The scripts assets/analysis_template.py and scripts/qc_analysis.py perform file system operations such as creating directories (os.makedirs) and saving files (data frames to CSV, plots to PDF). These actions are limited to the local environment and are strictly aligned with the bioinformatic analysis workflow.
  • [DATA_EXFILTRATION] (SAFE): No network operations (e.g., requests, curl, urllib) were found. Data processing is entirely local, and there are no signs of hardcoded credentials or sensitive file access beyond the provided data paths.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill relies on standard scientific libraries (scanpy, pandas, numpy, matplotlib) and does not attempt to download or execute remote scripts at runtime.
  • [PROMPT_INJECTION] (SAFE): No instructional overrides or attempts to bypass agent safety guidelines were identified in the script comments or documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM