cli-anything-geoai

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md shows commands that search and download open/public datasets (e.g., "data search" / "data download sentinel-2-l2a", "data download naip", "data download overture") which the agent is expected to ingest and process (raster/vector info, segmentation, vectorize), so untrusted third‑party content from those sources can materially influence analysis and downstream actions.