scanpy

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements standard bioinformatics workflows using widely recognized scientific libraries like Scanpy, Pandas, and Matplotlib. All code is transparent and aligned with its stated purpose of data analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface through loading H5AD, CSV, and 10X genomics files.
  • Ingestion points: Data loading occurs in scripts/qc_analysis.py and assets/analysis_template.py via Scanpy's read functions.
  • Boundary markers: Data is processed as structured bioinformatics data rather than natural language instructions.
  • Capability inventory: The skill's actions are restricted to local file reading, numerical data processing, and plot generation. It does not contain network exfiltration or arbitrary command execution capabilities.
  • Sanitization: Input handling relies on established parsing logic within the Scanpy and Pandas libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:23 AM
Security Audit — agent-trust-hub — scanpy