xiaohongshu-note-detail

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires the xsecToken to be inserted verbatim into navigation URLs and script parameters (e.g., navigate https://...?xsec_token={xsecToken}), which forces the LLM to handle/output a sensitive token value directly.

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

• Third-party content exposure detected (high risk: 0.95). The skill navigates to a Xiaohongshu note detail page and then runs extract-note-detail.py / extract-note-comments.py, which read window.__INITIAL_STATE__.note.noteDetailMap—this Vue state contains outsider-authored free text (the note body and commenters’ content) rendered from the public site at runtime.