Xiaohongshu Assistant

小红书运营助手。支持文案生成、标题优化、话题标签推荐、发布时间建议。

This skill's documentation and SKILL.md are consistent with a simple, safe content generator, but the included code contains account-management and a 'publisher' module that invokes external Python scripts via subprocess and looks for a sibling/parent 'XiaohongshuSkills' repository. Before installing or running: 1) If you only want copy-generation, avoid importing or executing xhs_publisher.py and xhs_accounts.py — use only xiaohongshu_assistant.py and templates.py. 2) Inspect any external scripts referenced (the XHS_SKILLS_DIR path) — if those scripts exist on your machine they would be executed by the publisher functions. 3) Remove or sandbox publisher/account modules (or delete them) if you don't want any automatic publishing or credential storage. 4) Do not run publish/login functions unless you trust and have inspected the external XiaohongshuSkills scripts and understand what tokens or cookies they require. These mismatches could be benign leftover code, but they increase risk — manual review and disabling of publisher paths is recommended.

Type: OpenClaw Skill Name: xiaohongshu-assistant Version: 1.0.0 The bundle contains modules (xhs_publisher.py and xhs_accounts.py) designed for automated browser control and account management via subprocess calls to an external repository (XiaohongshuSkills). While the main assistant logic in xiaohongshu_assistant.py includes a hardcoded 'safety mode' that intercepts publishing requests to prevent automated actions, the underlying high-risk capabilities for platform automation and local command execution remain present. The structure of providing functional automation scripts while claiming they are disabled in the UI creates a significant risk surface.