large-scale-map-visualization
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to the ingestion of untrusted external data in combination with high-privilege tool access.
- Ingestion points: The skill ingests untrusted location data via the
locationsarray in React components and geographic data results returned from Supabase RPC database calls. - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore potentially malicious content embedded within geographic data properties (e.g., place names or metadata).
- Capability inventory: The skill is granted access to high-privilege tools including
Bash,Write,Edit,WebSearch, andWebFetch. - Sanitization: While the code uses standard PostGIS functions for spatial queries, it does not explicitly demonstrate sanitization of user-controlled properties before they are rendered in HTML-based icons (
divIcon) or processed by the agent.
Audit Metadata