site-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Steps 2, 3, 5 and the "When generating a report" instructions) explicitly directs the agent to obtain and use open/public third‑party datasets (e.g., DEMs, FEMA flood maps, GTFS feeds, OSM/Overpass API, AirNow/AQI, municipal GIS) via the references/data-sources.md and API lists, so the agent would fetch and interpret untrusted public web content that can materially influence analysis and subsequent decisions.