read-weread-analyzer

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is fetched at runtime from the public WeRead user content APIs (e.g., /user/notebooks, /book/bookmarklist, /review/list/mine, /readdata/detail, /shelf/sync) inside scripts/fetch.py, then written to data.json and subsequently used for the LLM’s 10-dimension analysis.