stophy-places
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external sources, including Google Maps, Yelp, Tripadvisor, Airbnb, and Booking.com.
- Ingestion points: Web scraping results retrieved via the
stophy scrapecommand (e.g., saved to.stophy/places.jsonor processed via stdout). - Boundary markers: Absent. The instructions do not specify delimiters or provide warnings for the agent to ignore or isolate instructions potentially embedded in the scraped web content.
- Capability inventory: The skill utilizes Bash command execution to interact with the local filesystem and the
stophyCLI. - Sanitization: Absent. There is no mention of sanitization, filtering, or validation of the content retrieved from external websites before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill instructions utilize
npx @stophy/cli, which fetches and executes the vendor's CLI tool from the NPM registry. While this is a vendor-owned resource, it involves runtime downloading of executable code. - [COMMAND_EXECUTION]: The skill relies on shell command execution (
stophy scrape,stophy login) to perform scraping operations and manage authentication for external services.
Audit Metadata