arcgis-core-utilities

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly shows runtime HTTP fetching and ingestion (e.g., esriRequest(url, ...), promiseUtils.eachAlways([...fetch("/api/data1"), ...]) and urlUtils.addProxyRule referencing https://services.arcgis.com), indicating the agent will read and act on external/public HTTP resources whose untrusted/user-generated content could influence behavior.