scanpy
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external genomic files (H5AD, CSV, MTX), which represents an attack surface for indirect prompt injection via malicious metadata embedded in these datasets.
- Ingestion points:
sc.read_10x_mtx,sc.read_10x_h5,sc.read_h5ad, andsc.read_csvinSKILL.md. - Boundary markers: No delimiters or isolation instructions are present in the provided snippets.
- Capability inventory: The skill has file-write permissions (
adata.write,to_csv) and can execute local scripts (python scripts/qc_analysis.py). - Sanitization: No sanitization of input data metadata is demonstrated.
- [SAFE]: All external links point to official and reputable scientific documentation sites (e.g., scanpy.readthedocs.io, scverse.org).
- [SAFE]: The Python dependencies (scanpy, pandas, numpy) are standard, well-maintained libraries for bioinformatics and data science.
Audit Metadata