arcgis-3d-layers

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to load external 3D assets, which represents a surface for indirect instructions if the processed data contains malicious metadata or prompts. 1. Ingestion points: Remote URLs for IntegratedMesh3DTilesLayer and glTF model resources (resource.href) defined in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill utilizes network access to fetch remote assets and performs 3D rendering as described in SKILL.md. 4. Sanitization: The provided code does not include validation or sanitization logic for remote resources.
  • [EXTERNAL_DOWNLOADS]: The skill references external 3D models and tile services. These external references are standard and necessary for GIS visualization functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:38 AM