alterlab-geopandas

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

• Third-party content exposure detected (high risk: 0.70). The skill's documentation (references/data-io.md) explicitly shows reading remote, arbitrary URLs and cloud locations (e.g., gpd.read_file("https://example.com/data.geojson"), s3://..., HTTP/HTTPS examples), meaning the agent is expected to ingest untrusted third‑party data as part of its workflows and that data can materially affect downstream analysis and actions.