scanpy
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to facilitate bioinformatics data analysis using well-established Python libraries. All included scripts and documentation align with this intended use case.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a standard attack surface for indirect prompt injection as it is designed to ingest and process external data files.
- Ingestion points: The scripts
scripts/qc_analysis.pyandassets/analysis_template.pyusescanpyfunctions (e.g.,sc.read_h5ad,sc.read_10x_mtx,sc.read_csv) to load data from external sources into the agent's environment. - Boundary markers: No specific boundary markers or instructions to ignore embedded content are provided for the data ingestion steps.
- Capability inventory: The skill is capable of reading from and writing to the local filesystem (
adata.write,to_csv) and performing complex data transformations. - Sanitization: The skill relies on the underlying
scanpyandanndatalibrary parsers; no additional sanitization of the data content is implemented.
Audit Metadata