xiaohongshu-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and Command Reference explicitly instruct the agent to fetch and read public Xiaohongshu content (e.g., xhs read <id_or_url>, xhs comments "" --all, and the "URL to insights pipeline" that reads note pages and all comments from https://www.xiaohongshu.com), which are untrusted, user-generated social posts/comments that the agent is expected to parse and then may act on (e.g., like, comment, follow) — enabling indirect prompt injection from third-party content.