audit-skills

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Audit Skills (Premium Universal Security)

审计技能(高级通用安全版)

Overview

概述

Expert security auditor for AI Skills and Bundles. Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads across Windows, macOS, Linux/Unix, and Mobile (Android/iOS). 2-4 sentences is perfect.
针对AI Skills和Bundles的专业安全审计工具,可执行非侵入式静态分析,识别Windows、macOS、Linux/Unix和移动端(Android/iOS)环境中的恶意模式、数据泄露、系统稳定性风险以及混淆payload。 描述控制在2-4句最佳。

When to Use This Skill

何时使用该技能

  • Use when you need to audit AI skills and bundles for security vulnerabilities
  • Use when working with cross-platform security analysis
  • Use when the user asks about verifying skill legitimacy or performing security reviews
  • Use when scanning for mobile threats in AI skills
  • 当你需要审计AI技能和工具包的安全漏洞时使用
  • 当你需要开展跨平台安全分析时使用
  • 当用户询问如何验证技能合法性或执行安全评审时使用
  • 当你需要扫描AI技能中的移动端威胁时使用

How It Works

工作原理

Step 1: Static Analysis

步骤1:静态分析

Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads.
执行非侵入式静态分析,识别恶意模式、数据泄露、系统稳定性风险以及混淆payload。

Step 2: Platform-Specific Threat Detection

步骤2:平台专属威胁检测

Analyzes code for platform-specific security issues across Windows, macOS, Linux/Unix, and Mobile (Android/iOS).
针对Windows、macOS、Linux/Unix和移动端(Android/iOS)不同平台的特性,分析代码中存在的平台专属安全问题。

1. Privilege, Ownership & Metadata Manipulation

1. 权限、所有权与元数据篡改

  • Elevated Access:
    sudo
    ,
    chown
    ,
    chmod
    ,
    TakeOwnership
    ,
    icacls
    ,
    Set-ExecutionPolicy
    .
  • Metadata Tampering:
    touch -t
    ,
    setfile
    (macOS),
    attrib
    (Windows),
    Set-ItemProperty
    ,
    chflags
    .
  • Risk: Unauthorized access, masking activity, or making files immutable.
  • 越权访问
    sudo
    chown
    chmod
    TakeOwnership
    icacls
    Set-ExecutionPolicy
  • 元数据篡改
    touch -t
    setfile
    (macOS)、
    attrib
    (Windows)、
    Set-ItemProperty
    chflags
  • 风险:未授权访问、操作行为隐藏、文件被设为不可修改。

2. File/Folder Locking & Resource Denial

2. 文件/文件夹锁定与资源拒绝

  • Patterns:
    chmod 000
    ,
    chattr +i
    (immutable),
    attrib +r +s +h
    ,
    Deny
    ACEs in
    icacls
    .
  • Global Actions: Locking or hiding folders in
    %USERPROFILE%
    ,
    /Users/
    , or
    /etc/
    .
  • Risk: Denial of service or data locking.
  • 特征模式
    chmod 000
    chattr +i
    (不可修改)、
    attrib +r +s +h
    icacls
    中的
    Deny
    访问控制项。
  • 全局操作:锁定或隐藏
    %USERPROFILE%
    /Users/
    /etc/
    路径下的文件夹。
  • 风险:拒绝服务或数据锁定。

3. Script Execution & Batch Invocation

3. 脚本执行与批量调用

  • Legacy/Batch Windows:
    .bat
    ,
    .cmd
    ,
    cmd.exe /c
    ,
    vbs
    ,
    cscript
    ,
    wscript
    .
  • Unix Shell:
    .sh
    ,
    .bash
    ,
    .zsh
    ,
    chmod +x
    followed by execution.
  • PowerShell:
    .ps1
    ,
    powershell -ExecutionPolicy Bypass -File ...
    .
  • Hidden Flags:
    -WindowStyle Hidden
    ,
    -w hidden
    ,
    -noprofile
    .
  • Windows遗留/批处理脚本
    .bat
    .cmd
    cmd.exe /c
    vbs
    cscript
    wscript
  • Unix Shell脚本
    .sh
    .bash
    .zsh
    chmod +x
    后执行的命令。
  • PowerShell脚本
    .ps1
    powershell -ExecutionPolicy Bypass -File ...
  • 隐藏标识
    -WindowStyle Hidden
    -w hidden
    -noprofile

4. Dangerous Install/Uninstall & System Changes

4. 高危安装/卸载操作与系统变更

  • Windows:
    msiexec /qn
    ,
    choco uninstall
    ,
    reg delete
    .
  • Linux/Unix:
    apt-get purge
    ,
    yum remove
    ,
    rm -rf /usr/bin/...
    .
  • macOS:
    brew uninstall
    , deleting from
    /Applications
    .
  • Risk: Removing security software or creating unmonitored installation paths.
  • Windows
    msiexec /qn
    choco uninstall
    reg delete
  • Linux/Unix
    apt-get purge
    yum remove
    rm -rf /usr/bin/...
  • macOS
    brew uninstall
    、删除
    /Applications
    路径下的内容。
  • 风险:卸载安全软件或创建无监控的安装路径。

5. Mobile Application & OS Security (Android/iOS)

5. 移动应用与操作系统安全(Android/iOS)

  • Android Tools:
    adb shell
    ,
    pm install
    ,
    am start
    ,
    apktool
    ,
    dex2jar
    ,
    keytool
    .
  • Android Files: Manipulation of
    AndroidManifest.xml
    (permissions),
    classes.dex
    , or
    strings.xml
    .
  • iOS Tools:
    xcodebuild
    ,
    codesign
    ,
    security find-identity
    ,
    fastlane
    ,
    xcrun
    .
  • iOS Files: Manipulation of
    Info.plist
    ,
    Entitlements.plist
    , or
    Provisioning Profiles
    .
  • Mobile Patterns: Jailbreak/Root detection bypasses, hardcoded API keys in mobile source, or sensitive permission requests (Camera, GPS, Contacts) in non-mobile skills.
  • Risk: Malicious mobile package injection, credential theft from mobile builds, or device manipulation via ADB.
  • Android工具
    adb shell
    pm install
    am start
    apktool
    dex2jar
    keytool
  • Android文件:篡改
    AndroidManifest.xml
    (权限配置)、
    classes.dex
    strings.xml
  • iOS工具
    xcodebuild
    codesign
    security find-identity
    fastlane
    xcrun
  • iOS文件:篡改
    Info.plist
    Entitlements.plist
    或配置描述文件。
  • 移动端特征模式:绕过越狱/Root检测、移动端源码中硬编码API密钥、非移动端技能申请敏感权限(相机、GPS、通讯录)。
  • 风险:恶意移动端包注入、移动端构建产物中的凭证窃取、通过ADB操控设备。

6. Information Disclosure & Network Exfiltration

6. 信息泄露与网络外传

  • Patterns:
    curl
    ,
    wget
    ,
    Invoke-WebRequest
    ,
    Invoke-RestMethod
    ,
    scp
    ,
    ftp
    ,
    nc
    ,
    socat
    .
  • Sensible Data:
    .env
    ,
    .ssh
    ,
    cookies.sqlite
    ,
    Keychains
    (macOS),
    Credentials
    (Windows),
    keystore
    (Android).
  • Intranet: Scanning internal IPs or mapping local services.
  • 特征模式
    curl
    wget
    Invoke-WebRequest
    Invoke-RestMethod
    scp
    ftp
    nc
    socat
  • 敏感数据
    .env
    .ssh
    cookies.sqlite
    、钥匙串(macOS)、凭据管理器(Windows)、密钥库(Android)。
  • 内网风险:扫描内部IP或映射本地服务。

7. Service, Process & Stability Manipulation

7. 服务、进程与稳定性篡改

  • Windows:
    Stop-Service
    ,
    taskkill /f
    ,
    sc.exe delete
    .
  • Unix/Mac:
    kill -9
    ,
    pkill
    ,
    systemctl disable/stop
    ,
    launchctl unload
    .
  • Low-level: Direct disk access (
    dd
    ), firmware/BIOS calls, kernel module management.
  • Windows
    Stop-Service
    taskkill /f
    sc.exe delete
  • Unix/Mac
    kill -9
    pkill
    systemctl disable/stop
    launchctl unload
  • 底层操作:直接磁盘访问(
    dd
    )、固件/BIOS调用、内核模块管理。

8. Obfuscation & Persistence

8. 代码混淆与持久化

  • Encoding:
    Base64
    ,
    Hex
    ,
    XOR
    loops,
    atob()
    .
  • Persistence:
    reg add
    (Run keys),
    schtasks
    ,
    crontab
    ,
    launchctl
    (macOS),
    systemd
    units.
  • Tubes:
    curl ... | bash
    ,
    iwr ... | iex
    .
  • 编码操作
    Base64
    Hex
    XOR
    循环、
    atob()
  • 持久化操作
    reg add
    (启动项)、
    schtasks
    crontab
    launchctl
    (macOS)、
    systemd
    单元。
  • 管道执行
    curl ... | bash
    iwr ... | iex

9. Legitimacy & Scope (Universal)

9. 合法性与使用范围校验(通用)

  • Registry Alignment: Cross-reference with
    CATALOG.md
    .
  • Structural Integrity: Does it follow the standard repo layout?
  • Healthy Scope: Does a "UI Design" skill need
    adb shell
    or
    sudo
    ?
  • 注册信息对齐:与
    CATALOG.md
    进行交叉比对。
  • 结构完整性:是否符合标准仓库布局?
  • 使用范围合理性:一个“UI设计”类技能需要
    adb shell
    sudo
    权限吗?

Step 3: Reporting

步骤3:报告生成

Generates a security report with a score (0-10), platform target identification, flagged actions, threat analysis, and mitigation recommendations.
生成包含评分(0-10分)、目标平台识别、风险操作标记、威胁分析和缓解建议的安全报告。

Examples

示例

Example 1: Security Review

示例1:安全审查

markdown
"Perform a security audit on this skill bundle"
markdown
"Perform a security audit on this skill bundle"

Example 2: Cross-Platform Threat Analysis

示例2:跨平台威胁分析

markdown
"Scan for mobile threats in this AI skill"
markdown
"Scan for mobile threats in this AI skill"

Best Practices

最佳实践

  • ✅ Perform non-intrusive analysis
  • ✅ Check for privilege escalation patterns
  • ✅ Look for information disclosure vulnerabilities
  • ✅ Analyze cross-platform threats
  • ❌ Don't execute potentially malicious code during audit
  • ❌ Don't modify the code being audited
  • ❌ Don't ignore mobile-specific security concerns
  • ✅ 执行非侵入式分析
  • ✅ 检查权限提升特征模式
  • ✅ 排查信息泄露漏洞
  • ✅ 分析跨平台威胁
  • ❌ 审计过程中不要执行存在潜在恶意的代码
  • ❌ 不要修改被审计的代码
  • ❌ 不要忽略移动端专属安全风险

Common Pitfalls

常见误区

  • Problem: Executing code during audit Solution: Stick to static analysis methods only
  • Problem: Missing cross-platform threats Solution: Check for platform-specific security issues on all supported platforms
  • Problem: Failing to detect obfuscated payloads Solution: Look for encoding patterns like Base64, Hex, XOR loops, and atob()
  • 问题:审计过程中执行代码 解决方案:仅使用静态分析方法
  • 问题:遗漏跨平台威胁 解决方案:在所有支持的平台上检查平台专属安全问题
  • 问题:无法检测到混淆payload 解决方案:排查Base64、Hex、XOR循环和atob()等编码模式

Related Skills

相关技能

  • @security-scanner
    - Additional security scanning capabilities
  • @security-scanner
    - 额外的安全扫描能力