Security Audit

This runs a structured security audit on your codebase, checking for everything from hardcoded credentials and SQL injection to missing CSRF protection and outdated dependencies. It scans your files against a three-tier checklist (critical, medium, low severity), then generates a detailed report with specific line numbers, attack scenarios, and before/after code fixes for each issue. The output format is thorough, maybe even verbose, but that's the point when you need to hand security findings to your team. Best used when you're preparing for a release, onboarding legacy code, or just want to catch the obvious security mistakes before they become incidents. It won't replace dedicated security tools but gives you a solid first pass.

GitHub stars: 328
last updated: May 13, 2026

View on GitHub

Install

$ npx -y skills add laolaoshiren/claude-code-skills-zh --skill security-audit --agent claude-code

Installs into .claude/skills of the current project.

Files

代码安全审计

触发条件

当用户要求安全检查、漏洞扫描、安全审计、依赖安全检查时激活此技能。

工作流程

确定审计范围 — 根据用户指定的目录/文件/代码段进行分析
静态安全扫描 — 按检查清单逐项排查
依赖安全检查 — 检查 package.json / requirements.txt / go.mod 等依赖文件
生成审计报告 — 按严重程度分类输出

检查清单

🔴 高危

硬编码密钥/密码/API Key
SQL 注入风险（字符串拼接 SQL）
命令注入（未过滤的 shell 命令）
路径遍历（未校验的文件路径）
反序列化漏洞
未校验的 JWT/Token 验证

🟡 中危

🟢 低危

输出格式

## 🔒 安全审计报告

### 审计概览
- 审计范围：xxx
- 发现问题：🔴 高危 X 个 / 🟡 中危 X 个 / 🟢 低危 X 个

### 🔴 高危问题
#### 1. [文件路径:行号]
- **漏洞类型**：xxx
- **风险描述**：xxx
- **攻击场景**：攻击者可以通过 xxx 方式...
- **修复方案**：
  ```code
  // 修复前
  // 修复后

🟡 中危问题

...

🟢 低危问题

...

依赖安全

依赖名	当前版本	建议版本	风险

修复优先级建议

立即修复：...
本周修复：...
长期改进：...


## 注意事项
- 提供修复前后的代码对比
- 对于每条漏洞，说明具体的攻击向量
- 优先级基于可利用性和影响范围判断

SKILL.md on GitHub

Details

Repository: github.com/laolaoshiren/claude-code-skills-zh
Category: Security
License: MIT
First seen: Jun 11, 2026

More from laolaoshiren/claude-code-skills-zh

All 19