bilibili-video

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches metadata and user-generated "hot replies" from Bilibili public APIs (e.g., https://api.bilibili.com/x/web-interface/view and https://api.bilibili.com/x/v2/reply/main) and ingests those comments as part of its workflow (used for summarization), so untrusted third-party content can materially influence outputs or actions.