stophy-places
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including Google Maps, Tripadvisor, Airbnb, and Booking.com.
- Ingestion points: External reviews and search results are retrieved and stored in JSON files (e.g.,
.stophy/reviews.json,.stophy/tripadvisor-reviews.json). - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions potentially embedded in these external reviews.
- Capability inventory: The skill uses shell commands via
stophyandnpxto interact with the file system and network. - Sanitization: While results are stored in JSON format, there is no evidence of sanitization or filtering of the content before the agent interprets it.
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to executestophyCLI commands andnpxfor various travel search operations. - [EXTERNAL_DOWNLOADS]: The skill instructions include the use of
npx -y @stophy/cli, which downloads and executes the vendor's package at runtime.
Audit Metadata