datamol

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

• Third-party content exposure detected (high risk: 0.80). The skill's I/O functions explicitly support reading remote, public sources via fsspec (e.g., dm.read_sdf/dm.read_csv/dm.open_df with "s3://", "https://example.com/data.csv", HTTP/HTTPS) so the agent will fetch and parse arbitrary third-party/user-provided content.