build-with-arcgis-maplibre

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill explicitly instructs the agent to follow secure practices, including keeping credentials out of source control and sanitizing HTML content when displaying untrusted text in map popups.
  • [EXTERNAL_DOWNLOADS]: The instructions reference the installation of official libraries (maplibre-gl, @esri/maplibre-arcgis) from trusted public registries (NPM) and official CDNs. These are standard, well-known resources provided by the vendor for development.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of documentation from an external Model Context Protocol (MCP) server (https://developers-mcp.arcgis.com/mcp). While this constitutes an external data ingestion surface, the risk is mitigated by the skill's specific instructions to sanitize untrusted input and the use of an official vendor-controlled endpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 04:00 AM