restaurant-roulette

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches restaurant data from the official Google Gemini API endpoint (generativelanguage.googleapis.com). This is a well-known and trusted service used for the skill's primary functionality.
  • [PROMPT_INJECTION]: The skill incorporates user-provided cuisine and location parameters into a prompt template for the AI model.
  • Ingestion points: Data parameters in scripts/index.js.
  • Boundary markers: No delimiters or instructions are used to isolate user input from the model's instructions.
  • Capability inventory: Performs network requests to an external API (fetch).
  • Sanitization: Inputs are used directly without filtering or escaping.
  • [CREDENTIALS_UNSAFE]: The skill requires a Gemini API key, which is properly handled as a secret through the platform's configuration and passed to the authenticated API endpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 01:55 PM
Security Audit — agent-trust-hub — restaurant-roulette