openrouter

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and ingests content from the public OpenRouter API (https://openrouter.ai/api/v1) — see the GET /models and POST /chat/completions calls in openrouter.ts — returning external model listings and LLM responses that the agent reads and acts on, so untrusted third-party content can influence behavior.