小红书自动发布助手

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.

What this means

If approved and executed, the agent can post publicly from the user's Xiaohongshu creator account.

Why it was flagged

The skill can use browser automation to publish content to Xiaohongshu, which is a high-impact public action, although the workflow is disclosed and scoped to the stated purpose.

Skill content
browser → act → click publish button
Recommendation

Review the generated title, body, tags, and cover image carefully before approving publishing.

What this means

The agent can act through the logged-in Xiaohongshu session when publishing steps are approved.

Why it was flagged

The skill relies on an authenticated browser session for the user's Xiaohongshu account; this is expected for publishing but grants account-level authority in that browser context.

Skill content
OpenClaw browser tool — access to a browser with the user logged into 小红书 creator portal
Recommendation

Use a dedicated browser profile or sandbox session for the intended Xiaohongshu account, and do not approve publishing unless the account and content are correct.

What this means

Installing dependencies from untrusted sources could expose the local environment to supply-chain risk.

Why it was flagged

The skill documents package installation requirements despite having no formal install spec. This is common for an instruction-based skill, but users should install dependencies from trusted package sources.

Skill content
Python 3 with Pillow (`pip install Pillow` or `apt install python3-pil`)
Recommendation

Install Pillow and fonts using trusted system or Python package repositories, and avoid copying install commands from modified or untrusted versions of the skill.

What this means

Draft content may persist beyond the current interaction and could be referenced in later work.

Why it was flagged

The skill stores generated draft content in a persistent memory-style path, which is purpose-aligned but may retain planned marketing or personal content for later reuse.

Skill content
Save draft to `memory/xiaohongshu-draft.md`
Recommendation

Avoid putting sensitive or embargoed information in drafts unless you are comfortable with it being saved, and clear old drafts when no longer needed.

What this means

A scheduled workflow could repeatedly generate posting drafts or initiate the review process.

Why it was flagged

The skill describes optional scheduled use. It also says delivery should announce to the user's channel and elsewhere states never to auto-publish, so this appears disclosed and controlled rather than hidden persistence.

Skill content
This skill works with cron jobs for scheduled daily posting. Typical cron setup:
Recommendation

Configure cron jobs so they only draft or request approval, and do not allow scheduled runs to publish without explicit confirmation.