bilibili-viral-topic

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

• Third-party content exposure detected (high risk: 0.75). Required workflow calls public Bilibili JSON endpoints at runtime (e.g., /x/web-interface/search/type and /x/relation/stat), then ingests returned fields like title/author_name into the script’s output (Markdown/JSON), which can be placed into the agent’s LLM context as free text.