Security Review

在添加认证、处理用户输入、处理密钥、创建 API 端点或实现支付/敏感功能时使用此 skill。提供全面的安全检查清单和模式。

335 stars 37 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add zhukunpenglinyutong/ai-max --skill security-review
Manual install
git clone --depth 1 https://github.com/zhukunpenglinyutong/ai-max.git /tmp/ai-max
mkdir -p ~/.claude/skills
cp -r /tmp/ai-max/skills/security-review ~/.claude/skills/security-review

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 安全审查 Skill

此 skill 确保所有代码遵循安全最佳实践并识别潜在漏洞。

## 何时激活

- 实现认证或授权
- 处理用户输入或文件上传
- 创建新的 API 端点
- 处理密钥或凭证
- 实现支付功能
- 存储或传输敏感数据
- 集成第三方 API

## 安全检查清单

### 1. 密钥管理

#### ❌ 永不这样做
```typescript
const apiKey = "sk-proj-xxxxx"  // 硬编码的密钥
const dbPassword = "password123" // 在源代码中
```

#### ✅ 始终这样做
```typescript
const apiKey = process.env.OPENAI_API_KEY
const dbUrl = process.env.DATABASE_URL

// 验证密钥存在
if (!apiKey) {
  throw new Error('OPENAI_API_KEY not configured')
}
```

#### 验证步骤
- [ ] 没有硬编码的 API 密钥、令牌或密码
- [ ] 所有密钥都在环境变量中
- [ ] `.env.local` 在 .gitignore 中
- [ ] git 历史中没有密钥
- [ ] 生产密钥在托管平台(Vercel、Railway)中

### 2. 输入验证

#### 始终验证用户输入
```typescript
import { z } from 'zod'

// 定义验证 schema
const CreateUserSchema = z.object({
  email: z.string().email(),
  name: z.string().min(1).max(100),
  age: z.number().int().min(0).max(150)
})

// 处理前验证
export async function createUser(input: unknown) {
  try {
    const validated = CreateUserSchema.parse(input)
    return await db.users.create(validated)
  } catch (error) {
    if (error instanceof z.ZodError) {
      return { success: false, errors: error.errors }
    }
    throw error
  }
}
```

#### 文件上传验证
Read the full skill on GitHub

Details

Skill name
security-review
Path
skills/security-review/SKILL.md
License
MIT
Repo updated
11 February 2026

FAQ

What does the Security Review skill do?

在添加认证、处理用户输入、处理密钥、创建 API 端点或实现支付/敏感功能时使用此 skill。提供全面的安全检查清单和模式。

How do I install the Security Review skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add zhukunpenglinyutong/ai-max --skill security-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Security Review popular?

It lives in zhukunpenglinyutong/ai-max, which has 335 GitHub stars and 37 forks.

Related skills

TDD Workflow

335

zhukunpenglinyutong/ai-max

在编写新功能、修复 bug 或重构代码时使用此 skill。强制执行测试驱动开发,覆盖率要求 80% 以上,包括单元测试、集成测试和 E2E 测试。

Testing & QA37

Skill Security Auditor

151

mar-antaya/my-claude-skills

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this

SecurityIn 2 lists29

Better Auth Security Best Practices

230

better-auth/skills

Configure rate limiting, manage auth secrets, set up CSRF protection, define trusted origins, secure sessions and cookies, encrypt OAuth tokens, track IP addresses, and implement audit logging for Better Auth. Use when users need to secure their auth setup, prevent brute force attacks, or harden a Better Auth deployment.

SecurityIn 1 list38

Security Threat Model

517

dotslashsimran/simcraft

Threat-model the user's own app from its real code. Draws the data flow (actors, trust boundaries, data stores, external services) as a Mermaid diagram, finds threats per element with STRIDE, ranks them by likelihood times impact, then proves each top risk with a local failing test, fixes it, and keeps the test as a regression test. Covers auth, IDOR and tenant isolation, injection, SSRF, secrets, CORS/CSRF, uploads, webhooks, dependencies, abuse, and LLM-app risks like prompt injection through tool output. Writes THREAT_MODEL.md. Use when the user says "threat model", "security review of my a

Security39

Tech Stack Evaluator

1.2k

borghei/Claude-Skills

Evaluate and compare technology stacks with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.

SecurityIn 1 list217

Security Monitoring

581

claude-office-skills/skills

Automate security monitoring, threat detection, incident response, and compliance workflows

Security105

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.