route-handlers

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

• Third-party content exposure detected (high risk: 0.90). The skill's route handler examples explicitly ingest untrusted user-generated content via request.json()/formData (e.g., POST handlers in app/api/posts/route.ts and other POST examples) and even show an AI/LLM streaming example that forwards a user-provided "prompt" to OpenAI (AI/LLM Streaming in SKILL.md), so the agent clearly reads and processes arbitrary third‑party/user input.