mj-xhs-note-batch-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The workflow requires collecting and using full explore URLs (used verbatim in getnote save commands), which often include session/xsec tokens or other sensitive query parameters, forcing the LLM to handle and reproduce secret-bearing URLs.

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 ingested when the skill uses logged-in Chrome to collect Xiaohongshu /explore/{noteId} pages and then runs getnote note <note_id> --field web_content, where web_content is the note’s body text authored by the Xiaohongshu creator (not the operating user).