The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @cablate/mcp-google-map package from the NPM registry. This package belongs to the skill's vendor and is used to provide the underlying CLI functionality for geographic lookups.
[COMMAND_EXECUTION]: The skill relies on shell command execution via the pattern npx -y @cablate/mcp-google-map exec <tool> '<json_params>' to interact with Google Maps APIs. Each tool invocation is stateless and processes JSON parameters to return geographic data.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted third-party data from the Google Maps API, including user reviews, editorial summaries, and AI-generated summaries.
Ingestion points: Data is ingested through the maps_place_details, maps_search_places, and maps_explore_area tools defined in references/tools-api.md.
Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the skill instructions.
Capability inventory: The skill possesses shell execution capabilities via npx and network access through the underlying CLI tool.
Sanitization: The skill instructs the agent to summarize the useful results instead of returning raw JSON, which acts as a basic filter for the ingested content.

google-maps