neon-functions

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the user’s own request body/messages (e.g., AI SDK agent messages), which are not authored by the operating user; the skill’s runtime path is fetch(request) -> request.json() -> streamText({ messages }).