cesiumjs-core-utilities

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly documents using Resource.fetchJson/fetchText/fetchImage and Cesium3DTileset.fromUrl to fetch and ingest arbitrary external URLs (e.g., "https://api.example.com/..." and "https://example.com/tileset.json"), meaning the agent will read and act on untrusted third‑party web content as part of its workflow.