Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
小红书笔记创作技能
v2.0.0小红书笔记素材创作技能。当用户需要创建小红书笔记素材时使用这个技能。技能包含:根据用户的需求和提供的资料,撰写小红书笔记内容(标题+正文),生成图片卡片(封面+正文卡片),以及发布小红书笔记。
⭐ 5· 2.4k·24 current·24 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The repository contains rendering scripts (Python/Node), HTML/CSS templates, and a publish script — all expected for a Xiaohongshu note creator. However the registry metadata claims 'required env vars: none' and 'no install spec' despite the code requiring dependencies (playwright, xhs library, js-yaml/marked) and an XHS cookie for publishing. That mismatch between declared requirements and actual code is unexpected and should be resolved.
Instruction Scope
SKILL.md explicitly instructs the agent/user to obtain the user's Xiaohongshu login cookie (via browser dev tools), save it to memory or XHS_COOKIE env var, and to retrieve it later via a memory_search (memory/xhs-cookie.md). Directing the agent to read from agent memory and to store a full site cookie is sensitive: it increases the risk of accidental credential exposure or misuse. Otherwise the runtime instructions for rendering and publishing themselves are within the declared purpose.
Install Mechanism
There is no install spec in the registry metadata, but the package.json and requirements.txt and README instruct installing Python/Node dependencies (playwright, marked, js-yaml, the xhs client) and browser engines. Having runnable code without a declared install step is an incoherence: automated install won't occur, and manual install is required — which increases the chance of missing or incorrectly installed dependencies. The dependency set (playwright + browser binaries) is heavyweight but plausible for HTML->image rendering.
Credentials
Publishing requires the user's Xiaohongshu login cookie (XHS_COOKIE) or a cookie saved in agent memory, but the skill metadata lists no required env vars or primary credential. Requesting a full site cookie is proportional to 'publish' functionality, but because the skill did not declare this credential up front, it's a surprising and sensitive requirement. The instructions also recommend storing the cookie in the agent's memory store, which broadens access to the secret.
Persistence & Privilege
Skill flags show always:false and normal model invocation settings. The skill does not request permanent platform privileges. The SKILL.md suggests saving cookie to memory for reuse, which is normal for convenience but increases long‑term exposure risk — it's a usability choice, not an elevated platform privilege.
What to consider before installing
This skill appears to implement the advertised rendering and (optional) publish flows, but there are several things to check before installing or running it:
- Metadata mismatch: the registry lists no env vars or install steps, yet the repository requires Python/Node dependencies and (for publishing) an XHS cookie. Treat that as a sign to inspect/install dependencies manually rather than trusting automatic plumbing.
- Sensitive credential handling: publishing requires your Xiaohongshu session cookie. Never paste that into public places. Prefer keeping it in a local, encrypted secret store (not shared agent memory) and audit publish_xhs.py to confirm it only talks to Xiaohongshu and does not leak the cookie elsewhere.
- Memory use: SKILL.md suggests saving the cookie into agent memory and retrieving it (memory_search). Only permit that if you understand how your agent stores and protects memory — agent memory can persist across sessions and may be accessible to other skills or logs.
- Audit the publish script: before using publish functionality, open scripts/publish_xhs.py and confirm it uses a legitimate xhs client or official endpoints, and that it does not POST your cookie to any third-party servers. Also search code for unexpected network endpoints, logging of secrets, or obfuscated logic.
- Install dependencies deliberately: follow the README to install requirements (pip install -r requirements.txt, npm install) and playwright browsers in a controlled environment (preferably an isolated VM or container) if you will render or publish.
- Least privilege: if you must provide a cookie, consider creating a throwaway account or only use publish in dry-run mode until you trust the code.
If you want, I can:
- Highlight the exact lines in scripts/publish_xhs.py that access network endpoints and where the cookie is used, or
- Summarize requirements.txt and package.json to list the packages you will need to install and any potential risky dependencies.Like a lobster shell, security has layers — review code before you run it.
chinesevk97773f21tranpwx9d00q2p7yn811spzimage-generationvk97773f21tranpwx9d00q2p7yn811spzlatestvk97773f21tranpwx9d00q2p7yn811spzmarkdownvk97773f21tranpwx9d00q2p7yn811spzsocial-mediavk97773f21tranpwx9d00q2p7yn811spzxiaohongshuvk97773f21tranpwx9d00q2p7yn811spz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
