alterlab-anndata

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's I/O instructions (references/io_operations.md and SKILL.md "Reading data" / "Download from URL") explicitly show reading h5ad and Zarr stores from arbitrary URLs or S3/GCS (e.g., ad.read_h5ad(url), fsspec.get_mapper('https://...')/s3://...), which instruct the agent to fetch and interpret untrusted third-party content as part of workflows.