stophy-crawl
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, which fetches the CLI package from the official npm registry. This is a standard practice for utilizing Node.js-based tools and targets a well-known service. - [COMMAND_EXECUTION]: The skill executes various
stophyCLI commands (e.g.,map,crawl,batch scrape) to perform its primary function. These operations are scoped to the intended purpose of web data retrieval. - [INDIRECT_PROMPT_INJECTION]: As the skill is designed to crawl and read content from external websites, it possesses an attack surface where untrusted data from the web is ingested into the agent's context. This is an inherent risk of web scraping tools, and users should be aware that scraped content could contain instructions designed to influence the agent.
- Ingestion points: Website content retrieved via
stophy crawlandstophy batch scrape. - Boundary markers: Not explicitly defined in the skill instructions.
- Capability inventory: Execution of Bash commands for crawling and reporting status.
- Sanitization: Content is returned as scraped data for the agent to process.
Audit Metadata