expo-api-routes

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

• Third-party content exposure detected (high risk: 0.85). The required workflow shown in SKILL.md includes an API route that takes a runtime prompt from the incoming request body (await request.json()), and that free-form user-provided text is then placed into the LLM call as messages: [{ role: "user", content: prompt }], creating an indirect prompt-injection surface from outsider-authored input.