stophy-lead-gen
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @stophy/cli@latestto download and run the latest version of the vendor-specific CLI from the NPM registry. This is part of the intended functionality for web scraping. - [COMMAND_EXECUTION]: It executes the
stophyCLI tool and thejqJSON processor within a Bash environment to search for local businesses and extract contact information. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites such as Google Maps, Yelp, and LinkedIn. It manages the risk of malicious content from these sources by using structured parsing with
jqto specifically extract name, phone, and website fields rather than passing raw scraped text directly back to the agent's main context. - Ingestion points: External URLs from Google Maps, Yelp, and LinkedIn via the
stophy scrapecommand. - Boundary markers: Not explicitly defined in the provided file.
- Capability inventory: Execution of shell commands via the Bash tool.
- Sanitization: Uses
jqto validate and filter the JSON output from the scraper.
Audit Metadata