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 documentation (references/io_operations.md) explicitly shows reading from arbitrary URLs and remote stores (e.g., ad.read_h5ad(url, backed='r') and fsspec.get_mapper('https://...') / 's3://...'), so the agent would fetch and interpret untrusted public third‑party content.