blue-ribbon-nearby

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation specifies a dependency on a custom Node.js package named blue-ribbon-nearby. This package is required to execute the location resolution and search logic.
  • [DATA_EXFILTRATION]: The skill requests sensitive user location data, such as precise GPS coordinates or specific landmarks, and transmits this information to an external service named k-skill-proxy at the endpoint /v1/blue-ribbon/nearby. While this is part of the intended functionality, it involves sending PII to a non-standard third-party service.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes data from both user inputs and external restaurant survey endpoints.
  • Ingestion points: User-supplied location strings/coordinates and JSON data retrieved from bluer.co.kr domains.
  • Boundary markers: Absent. The instructions do not define delimiters to protect the agent from instructions embedded in the external data or user location input.
  • Capability inventory: The skill uses a Node.js module to perform network requests and manipulate local data.
  • Sanitization: Absent. The skill does not mention validation or sanitization steps for the data fetched from external URLs or provided by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:00 AM
Security Audit — agent-trust-hub — blue-ribbon-nearby