Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问clear审计通过

security安全

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

3,669

周安装

156

GitHub Stars

227

下载量

1,285
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:security(安全)
来源仓库:https://github.com/rshankras/claude-code-apple-skills
仓库路径:skills/security
安装命令:
npx skills add https://github.com/rshankras/claude-code-apple-skills --skill security
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/rshankras/claude-code-apple-skills --skill security

简介

security 用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。

  • 适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。
  • 使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时应先确认最小权限。
  • 应脱敏方式和操作边界,避免直接操作高风险资源。
  • 当前底部简介为空,需参考原始 SKILL.md 获取完整使用指南。

SKILL.md

Security Review for Apple Platforms

Comprehensive security guidance for iOS, macOS, and watchOS applications. Reviews code for vulnerabilities and provides secure implementation patterns.

When This Skill Activates

Use this skill when the user:

  • Asks for "security review" or "security audit"
  • Wants to implement "secure storage" or "Keychain"
  • Needs "Face ID", "Touch ID", or "biometric authentication"
  • Asks about "certificate pinning" or "network security"
  • Mentions "Data Protection" or "encryption"
  • Wants to store "sensitive data", "credentials", or "tokens"
  • Asks about "Secure Enclave" or hardware security

Review Process

Phase 1: Project Discovery

Identify the app's security surface:

# Find security-related code
Grep: "SecItem|Keychain|kSecClass"
Grep: "LAContext|biometryType|evaluatePolicy"
Grep: "URLSession|ATS|NSAppTransportSecurity"
Grep: "CryptoKit|SecKey|CC_SHA"

Determine:

  • Platform (iOS, macOS, watchOS, or multi-platform)
  • Sensitive data types (credentials, health data, financial, PII)
  • Authentication methods in use
  • Network communication patterns

Phase 2: Secure Storage Review

Load and apply: secure-storage.md

Key areas:

  • Keychain usage patterns
  • Data Protection classes
  • Secure Enclave for keys
  • Avoiding insecure storage (UserDefaults, files)

Phase 3: Authentication Review

Load and apply: biometric-auth.md

Key areas:

  • Face ID / Touch ID implementation
  • Fallback mechanisms
  • LAContext configuration
  • Keychain integration with biometrics

Phase 4: Network Security Review

Load and apply: network-security.md

Key areas:

  • App Transport Security configuration
  • Certificate pinning
  • TLS best practices
  • Secure API communication

Phase 5: Platform-Specific Review

Load and apply: platform-specifics.md

Key areas:

  • iOS: Data Protection, App Groups, Keychain sharing
  • macOS: Sandbox, Hardened Runtime, Keychain access
  • watchOS: Health data, Watch Connectivity security

Output Format

Present findings in this structure:

# Security Review: [App Name]

**Platform**: iOS / macOS / watchOS / Universal
**Review Date**: [Date]
**Risk Level**: Critical / High / Medium / Low

## Summary

| Category | Status | Issues |
|----------|--------|--------|
| Secure Storage | ✅/⚠️/❌ | X issues |
| Authentication | ✅/⚠️/❌ | X issues |
| Network Security | ✅/⚠️/❌ | X issues |
| Platform Security | ✅/⚠️/❌ | X issues |

---

## 🔴 Critical Vulnerabilities

Security issues that expose user data or enable attacks.

### [Issue Title]

**File**: `path/to/file.swift:123`
**Risk**: [What could happen if exploited]
**OWASP Category**: [If applicable]

**Vulnerable Code**:

// current insecure code


**Secure Implementation**:

// fixed secure code


---

## 🟠 High Priority Issues

Issues that weaken security posture.

[Same format as above]

---

## 🟡 Medium Priority Issues

Issues that should be addressed for defense in depth.

[Same format as above]

---

## 🟢 Recommendations

Security hardening suggestions.

[Same format as above]

---

## ✅ Security Strengths

What the app does well:

- [Strength 1]
- [Strength 2]

---

## Action Plan

1. **[Critical]** [First fix]
2. **[Critical]** [Second fix]
3. **[High]** [Third fix]...

Priority Classification

🔴 Critical

  • Credentials stored in plain text or UserDefaults
  • Disabled SSL/TLS validation
  • Hardcoded secrets or API keys
  • SQL injection or code injection vulnerabilities
  • Missing authentication on sensitive operations

🟠 High

  • Keychain without appropriate access controls
  • Missing biometric authentication for sensitive data
  • Weak cryptographic implementations
  • Overly permissive entitlements
  • Sensitive data in logs

🟡 Medium

  • Missing certificate pinning
  • Biometric fallback too permissive
  • Data Protection class could be stronger
  • Missing jailbreak/integrity detection

🟢 Low/Recommendations

  • Additional hardening measures
  • Defense in depth improvements
  • Code organization for security clarity

Quick Checks

Insecure Storage Detection

Grep: "UserDefaults.*password|UserDefaults.*token|UserDefaults.*secret|UserDefaults.*apiKey"
Grep: "\.write\(.*credential|\.write\(.*password"
Grep: "let.*apiKey.*=.*\"|let.*secret.*=.*\""

Insecure Network Detection

Grep: "http://(?!localhost|127\.0\.0\.1)"
Grep: "AllowsArbitraryLoads.*true"
Grep: "serverTrust|URLAuthenticationChallenge.*useCredential"

Sensitive Data in Logs

Grep: "print\(.*password|print\(.*token|NSLog.*credential"
Grep: "Logger.*password|os_log.*secret"

References

  • secure-storage.md - Keychain, Data Protection, Secure Enclave
  • biometric-auth.md - Face ID, Touch ID, LAContext
  • network-security.md - ATS, certificate pinning, TLS
  • platform-specifics.md - iOS vs macOS vs watchOS

External Resources

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

30.09%
按下载量换算387

Gemini CLI

24.24%
按下载量换算311

windsurf

14.88%
按下载量换算191

Codex

10.86%
按下载量换算140

OpenCode

8.15%
按下载量换算105

Cursor

3.56%
按下载量换算46

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills