skill-scanner

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill Scanner

Skill Scanner

Security audit tool for Clawdbot/MCP skills - scans for malware, spyware, crypto-mining, and malicious patterns.
一款针对Clawdbot/MCP技能的安全审计工具——可扫描恶意软件、间谍软件、加密货币挖矿程序以及恶意代码模式。

Capabilities

功能特性

  • Scan skill folders for security threats
  • Detect data exfiltration patterns
  • Identify system modification attempts
  • Catch crypto-mining indicators
  • Flag arbitrary code execution risks
  • Find backdoors and obfuscation techniques
  • Output reports in Markdown or JSON format
  • Provide Web UI via Streamlit
  • 扫描技能文件夹中的安全威胁
  • 检测数据泄露模式
  • 识别系统篡改尝试
  • 捕捉加密货币挖矿行为特征
  • 标记任意代码执行风险
  • 发现后门程序和代码混淆技术
  • 以Markdown或JSON格式输出报告
  • 通过Streamlit提供Web UI

Usage

使用方法

Command Line

命令行

bash
python skill_scanner.py /path/to/skill-folder
bash
python skill_scanner.py /path/to/skill-folder

Within Clawdbot

在Clawdbot中使用

"Scan the [skill-name] skill for security issues using skill-scanner"
"Use skill-scanner to check the youtube-watcher skill"
"Run a security audit on the remotion skill"
"Scan the [skill-name] skill for security issues using skill-scanner"
"Use skill-scanner to check the youtube-watcher skill"
"Run a security audit on the remotion skill"

Web UI

Web界面

bash
pip install streamlit
streamlit run streamlit_ui.py
bash
pip install streamlit
streamlit run streamlit_ui.py

Requirements

环境要求

  • Python 3.7+
  • No additional dependencies (uses Python standard library)
  • Streamlit (optional, for Web UI)
  • Python 3.7+
  • 无额外依赖项(使用Python标准库)
  • Streamlit(可选,用于Web界面)

Entry Point

入口文件

  • CLI:
    skill_scanner.py
  • Web UI:
    streamlit_ui.py
  • CLI:
    skill_scanner.py
  • Web UI:
    streamlit_ui.py

Tags

标签

#security #malware #spyware #crypto-mining #scanner #audit #code-analysis #mcp #clawdbot #agent-skills #safety #threat-detection #vulnerability
#security #malware #spyware #crypto-mining #scanner #audit #code-analysis #mcp #clawdbot #agent-skills #safety #threat-detection #vulnerability