shiny-locations
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external sources that is then provided to the agent context.
- Ingestion points: The
IGeocoder.ReverseGeocodemethod fetches address information (Placemarkrecords) from native platform geocoders or the OpenStreetMap Nominatim API. These strings (e.g.,FormattedAddress,Name,Locality) are external content that an agent processes. - Boundary markers: The provided documentation does not specify the use of delimiters or 'ignore' instructions when presenting geocoding results to the LLM.
- Capability inventory: The skill includes the ability to read current GPS coordinates, monitor geofence events, perform network requests for geocoding, and write to a local SQLite database (via
Shiny.Geofencing.Regions.DocumentDb). - Sanitization: There is no explicit mention of sanitization for the strings returned by external geocoding services before they are interpolated into agent prompts.
Audit Metadata