bilibili-portfolio-search

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

• Third-party content exposure detected (high risk: 0.75). Runtime path: scripts/fetch_user_works.py calls https://doubaoya.com/.../bilibili-user-works/call, then parses the JSON response and prints envelope["data"] (including outsider-authored B站作品标题/链接) to stdout, which the agent will ingest as LLM context.