Xiaohongshu Operate
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may operate through whichever Xiaohongshu account is logged into the `openclaw` profile. If the wrong account or session is active, drafts or replies could be made under that identity, and private-message handling may be unintentionally in scope.
This shows the skill depends on a persistent browser/account profile and also contemplates private-message tasks. The artifacts do not clearly identify which account/session is in scope or require a separate credential/profile confirmation.
固定使用内置浏览器 profile：`openclaw`。 ... 评论与私信任务开始前必须先读取 `persona.md`
Before use, explicitly confirm the Xiaohongshu account and browser profile, declare the profile/session dependency, limit actions to that account, and require separate approval before any private-message access or public sending.
A confirmed reply can still be posted from the user’s account and affect reputation or platform standing.
The skill automates a social-platform reply workflow, which can affect a public account, but it includes review, confirmation, and default volume limits.
默认 `mode=check_then_reply`：先检查汇总，再等待用户确认后发送。 ... 一轮默认发送 1 条
Review each proposed reply, verify the target comment and account, and only confirm sends that you are comfortable posting publicly.