xhs-note-breakdown

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow ingests outsider-authored free text at runtime via “note link, screenshots, or pasted copy,” which can include an external Xiaohongshu note’s title/caption/comments/transcript and is therefore user-supplied content that the LLM must parse and break down.