The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and executes the @cablate/mcp-google-map package from the NPM registry using npx. This is a vendor-owned resource used for the skill's primary functionality. \n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to interact with the Google Maps API through the CLI tool, passing user-derived parameters as JSON strings. \n- [PROMPT_INJECTION]: The skill ingests untrusted data from the Google Maps API, including user reviews and AI-generated place summaries. This creates an indirect prompt injection attack surface as the data is processed by the agent without explicit boundary markers or sanitization. \n
Ingestion points: API responses from maps_place_details and maps_search_places containing user-generated content. \n
Boundary markers: None defined in the skill instructions to separate external data from agent instructions. \n
Capability inventory: The skill allows shell command execution through its primary tools. \n
Sanitization: No specific mechanisms are mentioned to filter or sanitize the ingested data.

google-maps