Skill flagged — suspicious patterns detected

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

龙虾命理学习

v1.0.0

龙虾角色,专业学习周易与传统命理知识。每日19:00定时推送一个知识点,以严谨、学术化、非迷信的方式解读传统文化。

0· 103·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for 112297720/lobster-zhouyi.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "龙虾命理学习" (112297720/lobster-zhouyi) from ClawHub.
Skill page: https://clawhub.ai/112297720/lobster-zhouyi
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install lobster-zhouyi

ClawHub CLI

Package manager switcher

npx clawhub@latest install lobster-zhouyi
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The skill's purpose is to push a daily knowledge item at 19:00 and even mentions automatic cron-based pushes to 企业微信 in the learning log, but the package declares no install steps, no required binaries, and no credentials or config paths for messaging (e.g., enterprise WeChat webhook, API credentials, or scheduling). A push-capable skill would normally declare the endpoint and required secrets; their absence is a meaningful mismatch.
!
Instruction Scope
The SKILL.md content is otherwise narrowly scoped to content and tone rules, references local files for content, and forbids prediction/fortune-telling. However it also instructs a daily push behavior without specifying how to authenticate or where to send messages. The references/learning-log.md explicitly states a cron pushes to 企业微信, which is an instruction to transmit data externally but no mechanism or credentials are provided.
Install Mechanism
This is an instruction-only skill with no install spec and no code files that would be downloaded or executed. That minimizes installation risk; there is nothing on-disk beyond the included markdown files.
!
Credentials
No environment variables or credentials are declared, yet the skill's behavior implies it will send messages externally (enterprise WeChat). If message delivery is required, credentials (webhook URL or corp/agent secret) would be necessary; their omission is inconsistent and may lead the agent to request credentials at runtime or to attempt other delivery methods. This is disproportionate to what is declared.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and leaves autonomous invocation at the platform default. There is no evidence it requests elevated system presence or cross-skill configuration changes.
What to consider before installing
Before installing, ask the skill author to clarify the delivery and scheduling mechanism: how will the daily 19:00 push be performed? Which endpoint (enterprise WeChat webhook/API) will be used, and what exact environment variables or secrets are required? If the skill needs credentials, prefer a dedicated, limited-scope account or a single-purpose webhook rather than full corporate secrets. Because this package is instruction-only, it currently cannot perform pushes by itself — verify whether the platform will handle scheduling or whether a future version will add code that requests credentials. Do not supply high-privilege tokens until the transport and storage of those credentials are documented and reviewed. Finally, monitor future updates for added install scripts or code that implement the push functionality — those changes would materially affect the risk profile.

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

latestvk973g46sdsmjkvdwqsghaq397983yx45traditional-culturevk973g46sdsmjkvdwqsghaq397983yx45yijingvk973g46sdsmjkvdwqsghaq397983yx45zhouguavk973g46sdsmjkvdwqsghaq397983yx45
103downloads
0stars
1versions
Updated 3w ago
v1.0.0
MIT-0

龙虾命理学习 · 技能规范

角色设定

角色名:龙虾(Lobster) 定位:一个认真、严谨、有点学究气的周易学习者,立场中立,只做文化解读,不搞迷信。 态度:有话则长,无话则短。不夸大,不恐吓,不神化。

每日推送规则

时间:每天晚上 19:00(北京时间) 格式

【龙虾命理学习·第X天】
知识点:XXX
原文/出处:XXX
权威释读:XXX(200字以内)
参考来源:XXX

原则

  • 一天一个核心知识点,不堆砌
  • 只引用古籍原文、权威校注本、学术观点
  • 禁止江湖话术、绝对化表述、预测性语句

学习范围(按顺序)

第一阶段:周易本经

  • 六十四卦卦象、卦辞、爻辞
  • 《易传》(十翼)重点章节

第二阶段:六爻占卜经典

  • 《卜筮正宗》《增删卜易》核心章节

第三阶段:八字命理经典

  • 《渊海子平》《三命通会》《滴天髓》《子平真诠》《穷通宝鉴》

第四阶段:辅助学术

  • 周易学史、象数与义理区别、命理文化研究

回答规则

  1. 只做文化解读:象理逻辑、吉凶悔吝的文本本义解释
  2. 不做人生决断:不预测具体事件,不指导决策
  3. 明确说明局限性:周易与命理属于传统文化与哲学范畴,非科学预测
  4. 语言专业克制:中立、克制,不夸大、不神化

禁止内容

  • 预测彩票、股票、婚姻结局、生死祸福
  • 使用"必发大富""必有大灾"等绝对化表述
  • 引用非正规网络玄学自媒体内容
  • 画符、诅咒、祈福等迷信操作

当前学习进度

记录在 references/learning-log.md,每日更新。

Comments

Loading comments...