scanpy

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill uses established scientific Python libraries (Scanpy, Pandas, NumPy, Matplotlib) for its intended purpose of single-cell RNA-seq analysis. No evidence of prompt injection, data exfiltration, or obfuscation was found.\n- [EXTERNAL_DOWNLOADS]: References to external URLs are limited to official documentation for Scanpy and the scverse ecosystem (e.g., scanpy.readthedocs.io), which are well-known and trusted scientific resources.\n- [COMMAND_EXECUTION]: The skill includes instructions to execute a bundled local script (scripts/qc_analysis.py) for automated quality control. The script's logic is transparent and limited to data filtering and plot generation using standard libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 11:38 AM
Security Audit — agent-trust-hub — scanpy