dask

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

• Third-party content exposure detected (low risk: 0.10). The skill contains instructions and code examples for reading data files such as CSV, JSON, and Parquet (e.g., using dd.read_csv, db.read_text, etc.), which could ingest user-supplied data files containing arbitrary free text, presenting an indirect prompt injection risk through file ingestion.