arcgis-portal-content

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the ArcGIS SDK and Calcite components from Esri's official CDN (js.arcgis.com). These are well-known and trusted sources for GIS application development.\n- [PROMPT_INJECTION]: The skill provides patterns for processing metadata from ArcGIS Portal items (like titles and bookmark names), which could contain externally-controlled content. This represents a potential surface for indirect prompt injection.\n
  • Ingestion points: Data is ingested through PortalItem.load(), portal.queryItems(), and UI components like arcgis-bookmarks in SKILL.md.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are used in the provided examples.\n
  • Capability inventory: The skill allows the agent to perform actions such as map.save(), map.saveAs(), item.update(), and view.goTo().\n
  • Sanitization: The examples do not demonstrate input sanitization, notably using direct string interpolation for SQL-like filters (e.g., where: "Name = '${bookmarkName}'"). Users should implement appropriate input validation when using these patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 06:14 PM
Security Audit — agent-trust-hub — arcgis-portal-content