Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

ZeeLin AI Twitter博主信息简报

ZeeLin AI Twitter博主信息简报生成与自动发推。从指定AI博主账号抓取近10天推文 → 整理成中文高信号简报 → 提炼英文推文 → 发布到用户X账号。触发关键词:AI博主简报、爬取推文、信息简报发推、x-creator-briefing、AI简报、博主推文汇总、抓近10天推文、整理简报发推。

MIT-0 · Free to use, modify, and redistribute. No attribution required.
0 · 32 · 0 current installs · 0 all-time installs
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The described workflow (use a browser-driven scraper to fetch recent tweets, produce a Chinese briefing, extract an English tweet, and delegate posting to a Twitter/X autopost skill) is internally consistent for the stated goal. It does not request credentials itself and relies on an autopost skill for publishing, which is a reasonable delegation. However, the SKILL.md explicitly points to local filesystem paths for other skills (~/.openclaw/workspace/skills/...), which is not strictly required to perform the described workflow and is disproportionate to the minimal needs of a summarization/posting pipeline.
!
Instruction Scope
Instructions tell the agent to open creators' pages with agent-browser and scrape up to 20 tweets per account (normal for browser-based scraping). They also instruct the agent to read SKILL.md files of other skills by absolute path. Directly reading other skills' files (even if SKILL.md) expands scope beyond the described task and could expose unrelated configuration or secrets. The skill does state it will ask for user confirmation before posting unless user granted 'auto' permission, which is a good control.
Install Mechanism
Instruction-only skill with no install spec and no code files—lowest install risk. Nothing is downloaded or written by an installer.
Credentials
The skill requests no environment variables or credentials itself, which is plausible because it delegates posting to a separate autopost skill. That delegation is acceptable if the autopost skill manages credentials. However, the explicit instruction to read other skills' files raises a credential-proportionality concern: those files might reference tokens or contain sensitive config; reading arbitrary skill directories is not justified by the stated purpose.
Persistence & Privilege
always is false and there is no indication the skill attempts to persist itself or modify other skills' configs. Autonomous invocation is allowed by default (disable-model-invocation false), which is normal for skills but increases the importance of the other concerns noted above.
What to consider before installing
This skill appears to do exactly what it says (scrape recent tweets, summarize, and post), but check two things before installing: 1) Confirm you trust the referenced 'ZeeLin Twitter/X AutoPost' and 'agent-browser' skills—they will handle login/posting and may hold your tokens. 2) Ask the author why the skill needs to read files under ~/.openclaw/workspace/skills; reading other skills' files is not required to scrape or summarize and could expose unrelated sensitive data. If you proceed, require explicit user confirmation before any automatic posting and limit the agent's filesystem permissions (or run in a sandbox) so it cannot read unrelated skill directories.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.0
Download zip
latestvk97fe5s47syxp4x3mg99byf1d983v0hz

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

SKILL.md

AI Twitter博主信息简报

工作流(4步)

  1. 抓推文 — 用 agent-browser 打开每位博主主页,抓近10天内容(最多20条/人)
  2. 整理简报 — 提炼高信号内容,按主题聚合,写中文简报,保存到 reports/x-creator-briefing-YYYY-MM-DD.md
  3. 提炼英文推文 — 从简报中提炼1条精炼英文推文(≤240字),高价值内容摘要
  4. 发推 — 用 ZeeLin Twitter/X AutoPost skill 发布英文推文

默认博主列表

references/bloggers.md,包含18位AI/AIGC/工具博主。可按用户指令临时增减。

简报格式

# AI 博主动态简报 YYYY-MM-DD

## 🔥 高信号主线
- 主题1:[摘要](来源 @handle)
- 主题2:[摘要]

## 📌 各账号亮点
### @handle
- 要点1
- 要点2

## ⚠️ 未检索到近期内容
- @handle(原因)

英文推文格式

🧵 AI Signal Briefing [date]

Key themes from top AI creators:
• [insight 1] (@handle)
• [insight 2] (@handle)
• [insight 3]

#AI #AITools #BuildInPublic

注意事项

  • 打开 X 需要用户已在浏览器登录
  • 若某账号内容抓取失败,在简报末尾标注,不中断整体流程
  • 发推前展示英文推文内容给用户确认(除非用户明确说自动发)
  • 如需读取 agent-browser skill,路径:~/.openclaw/workspace/skills/agent-browser-clawdbot/SKILL.md
  • 如需读取 Twitter autopost skill,路径:~/.openclaw/workspace/skills/zeelin-twitter-web-autopost/SKILL.md

Files

2 total
Select a file
Select a file to preview.

Comments

Loading comments…