google-maps-travel-planning
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
@cablate/mcp-google-mappackage vianpxto execute travel planning tools. This command execution is the primary function of the skill and uses vendor-owned resources. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Google Maps API, including place reviews and descriptions, which constitutes a standard attack surface for indirect prompt injection. The skill instructions remind the agent to adhere to content attribution but do not explicitly define boundary markers for untrusted API data.
- Ingestion points: Data enters the context through
maps_place_detailsandmaps_search_along_route(SKILL.md, references/travel-planning.md). - Boundary markers: No explicit delimiters are specified for the external content.
- Capability inventory: The skill has shell execution capabilities via
npxand network access through the Maps CLI (SKILL.md). - Sanitization: No specific data sanitization or filtering logic is described for the retrieved place details.
Audit Metadata