anndata
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include installing the
anndatapackage and its optional extras (dask, lazy, openpyxl, loompy, s3fs, gcsfs) from the official PyPI registry using theuvpackage manager.- [INDIRECT_PROMPT_INJECTION]: The skill processes various external genomics and data formats, which constitutes a potential ingestion point for untrusted content. - Ingestion points: The skill utilizes several data loading functions in
SKILL.mdandreferences/io_operations.mdincludingad.read_h5ad(),ad.read_zarr(), and specialized readers fromanndata.io. - Boundary markers: No explicit markers to distinguish data from instructions are used in the data processing examples.
- Capability inventory: The skill has access to file-system operations (Read, Write, Edit) and shell execution (Bash) via platform configuration.
- Sanitization: No specific sanitization of input data content or metadata values is demonstrated in the provided code snippets.
Audit Metadata