geopandas

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

• Third-party content exposure detected (high risk: 0.80). This skill's data-io documentation explicitly shows reading from arbitrary HTTP/HTTPS URLs and file-like inputs (e.g., gpd.read_file("https://example.com/data.geojson"), S3/az:// paths, and StringIO), which means the agent can fetch and parse untrusted user-provided third‑party content as part of its workflow.