The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install standard Node.js dependencies (such as typescript, bottleneck, and express) from public registries and makes network requests to the RapidAPI service domain (maps-data.p.rapidapi.com).
[DATA_EXPOSURE]: The skill provides instructions for managing sensitive API keys using environment variables or .env files, aligning with secure development best practices for secret management.
[INDIRECT_PROMPT_INJECTION]: The skill identifies potential attack surfaces where untrusted data enters the agent's context during processing.
Ingestion points: Search queries and location strings are accepted via CLI arguments in src/index.ts and web form inputs in src/server.ts; business data is retrieved from the RapidAPI response in src/client.ts.
Boundary markers: Absent. The skill does not explicitly use delimiters to separate external data from system instructions.
Capability inventory: The skill has capabilities to write to the local file system (src/csv.ts) and perform network requests (src/client.ts).
Sanitization: Business data is escaped for CSV formatting in src/csv.ts to prevent CSV injection, though no specific sanitization for LLM-based indirect injection is present.

google-maps-scraper