arcgis-core-maps

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly shows fetching and loading external, public resources — e.g., esriRequest(url, ...) examples and loading WebMap/WebScene via portalItem IDs and external TileLayer/ElevationLayer URLs (such as https://astro.arcgis.com/...), which the agent is expected to ingest and use to configure views and features, so untrusted third-party content could materially influence behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill includes CDN script tags that are fetched and executed at runtime (e.g., https://js.arcgis.com/4.34/, https://js.arcgis.com/calcite-components/3.3.3/calcite.esm.js, and https://js.arcgis.com/4.34/map-components/), which are required for the CDN usage and therefore execute remote code in the client.