google-maps-leads

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides structured instructions for the agent to use a browser tool to automate tasks such as navigating search results, scrolling to trigger lazy-loading of content, and clicking through to individual business listings.
  • [EXTERNAL_DOWNLOADS]: The instructions guide the agent to access Google Maps and various external business websites. It also references an external proxy service provider for routing browser traffic.
  • [PROMPT_INJECTION]: The skill involves scraping and processing data from external, untrusted websites, which presents an indirect prompt injection surface.
  • Ingestion points: Business listing details from Google Maps and content from external business websites (e.g., contact and about pages).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are included for the scraped content.
  • Capability inventory: The agent uses a browser tool for navigation, interaction, and data extraction.
  • Sanitization: No sanitization or validation of the scraped text is defined before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 08:23 AM
Security Audit — agent-trust-hub — google-maps-leads