arcgis-3d-layers

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows runtime creation of layers that load public URLs (e.g., SceneLayer/PointCloudLayer/VoxelLayer with "https://tiles.arcgis.com/tiles/.../SceneServer", IntegratedMesh3DTilesLayer with "https://example.com/tileset.json", and glTF resources like "https://example.com/model.glb") and uses those loaded resources (await layer.load(), popupTemplate content, queryFeatures, renderer selection, applyEdits) as part of the workflow, meaning untrusted third-party content would be fetched and interpreted and could materially influence agent behavior.