NYC

openrouter

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • [SAFE] (SAFE): Analysis of the README.md, QUICK_REFERENCE.md, and metadata.json confirms the skill is entirely instructional and poses no security risk to the agent or host system.
  • [CREDENTIALS_SAFE] (LOW): The skill correctly demonstrates using environment variables (OPENROUTER_API_KEY) and includes explicit 'Security' sections warning against exposing keys in frontend code.
  • [EXTERNAL_DOWNLOADS] (LOW): References the official and widely-trusted 'openai' npm package as the primary SDK for implementation.
  • [PROMPT_INJECTION] (SAFE): No instructions were found that attempt to subvert the agent's system prompt or bypass safety guardrails.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 09:36 PM