blue-ribbon-nearby

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill depends on a Node.js package titled blue-ribbon-nearby to handle the core logic of resolving locations and searching for restaurants. This package is consistent with the skill's identity and is considered a vendor-owned resource.
  • [COMMAND_EXECUTION]: The skill executes JavaScript code through the blue-ribbon-nearby module to perform API queries and data processing.
  • [DATA_EXFILTRATION]: User-provided location data (such as coordinates, districts, or landmarks) is transmitted to official Blue Ribbon Survey endpoints and a proxy service (k-skill-proxy) to fetch restaurant results. This transmission is necessary for the skill's primary functionality.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted user input (location strings) to drive network requests.
  • Ingestion points: User-provided location strings entered during the mandatory first question interaction.
  • Boundary markers: Absent; there are no specific delimiters or instruction-ignore wrappers defined for the location input.
  • Capability inventory: Network operations and restaurant data retrieval via blue-ribbon-nearby and k-skill-proxy.
  • Sanitization: Not explicitly defined in the skill instructions; the skill relies on the underlying module for input handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 06:21 AM