dask

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

• Third-party content exposure detected (high risk: 0.70). The skill's documentation and workflow explicitly show reading and parsing external, potentially untrusted files (e.g., SKILL.md and references/bags.md examples like db.read_text('logs/.json').map(json.loads') and references/dataframes.md showing dd.read_parquet('s3://mybucket/data/.parquet')), and those parsed records are used to drive computations and dynamic task submission (futures), so third‑party/user‑generated content is ingested and can influence subsequent tool actions.