google-maps-lead-scraping
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from Google Maps listings and business reviews, which represents a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read business names, categories, and review text from external sources.
- Capability inventory: The skill utilizes the ManyPI tool for network-based lead enrichment and search.
- Sanitization: No specific delimiters or safety instructions are provided to sanitize external content before processing.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to add a tool via an external MCP endpoint hosted on the author's infrastructure.
- Finding: The skill includes the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s userto integrate the ManyPI lead generation service.
Audit Metadata