xiaohongshu-note-analyzer

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

• Third-party content exposure detected (high risk: 0.85). 运行时会调用 scripts/fetch_xhs_trends.py 通过 RedFoxHub 接口获取全网爆款笔记的 title/desc/userName 等字段，并在 format_output() 中把这些“外部作者内容”拼成 Markdown（含作者名与作品链接）后进入 LLM 上下文用于评分与“参考爆款笔记”展示。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime script (scripts/fetch_xhs_trends.py) calls the external API https://redfox.hk/story/api/cozeSkill/getXhsCozeSkillData to fetch viral note data that is injected and used to drive scoring, reference notes, and generation behavior, so the external content directly controls the agent's outputs.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (2 type(s) found)