location-ar-experience

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements logic for fetching AR content and metadata from external sources, which constitutes a vulnerability surface for indirect injection attacks.
  • Ingestion points: Data is fetched through api.get_content_for_tile in the SpatialContentLoader class in SKILL.md.
  • Boundary markers: There are no defined delimiters or warnings within the data model to identify or ignore instructions embedded in the external content.
  • Capability inventory: The skill includes code patterns for performing network requests and accessing local storage for state persistence.
  • Sanitization: No methods for validating, filtering, or escaping the external content are included in the provided implementation patterns.
  • [EXTERNAL_DOWNLOADS]: The skill references external dependencies and cloud infrastructure required for geospatial AR functionality.
  • Fetches the ARCore library from Google's official package registry for Android development.
  • Interacts with remote cloud services for the storage and retrieval of spatial anchors via the CloudService interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:22 PM