stophy-shopping
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites, including product descriptions and user reviews from Amazon, TikTok Shop, eBay, and Trustpilot. This content could be manipulated by third parties to influence agent behavior.
- Ingestion points: Untrusted data enters the agent context via the
stophy scrapecommand which retrieves content from various external URLs (Amazon, TikTok, eBay, Craigslist, Trustpilot). - Boundary markers: The skill instructions do not specify any delimiters or safety markers to help the agent distinguish between its instructions and the data being processed.
- Capability inventory: The skill has access to shell command execution (
stophy) and file system write operations (-o .stophy/amazon.json). - Sanitization: There is no explicit sanitization or filtering of the scraped web content before it is returned to the agent.
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npxto fetch and execute its own CLI tool. - Evidence: The
allowed-toolssection includesBash(npx @stophy/cli@latest *). This pattern downloads and executes the latest version of the@stophy/clipackage from the NPM registry at runtime. - [COMMAND_EXECUTION]: The skill relies on executing shell commands via the
stophyCLI to perform its primary functions. - Evidence: The "Quick start" section provides multiple examples of command execution, such as
stophy scrape "https://www.amazon.com/s?k=laptop&low-price=300&high-price=900" --parser amazon-search --json -o .stophy/amazon.json.
Audit Metadata