Skills for Real Engineers. Straight from my .agents directory.
How to install security-audit
npx skills add laolaoshiren/claude-code-skills-zh# or add only this skill to Claude Code: copy the folder
skills/security-audit/
# into
~/.claude/skills/security-audit/ (all projects)
.claude/skills/security-audit/ (one project)
1# 代码安全审计23## 触发条件4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。56## 工作流程781. **确定审计范围** — 根据用户指定的目录/文件/代码段进行分析92. **静态安全扫描** — 按检查清单逐项排查103. **依赖安全检查** — 检查 package.json / requirements.txt / go.mod 等依赖文件114. **生成审计报告** — 按严重程度分类输出1213## 检查清单1415### 🔴 高危16- [ ] 硬编码密钥/密码/API Key17- [ ] SQL 注入风险(字符串拼接 SQL)18- [ ] 命令注入(未过滤的 shell 命令)19- [ ] 路径遍历(未校验的文件路径)20- [ ] 反序列化漏洞21- [ ] 未校验的 JWT/Token 验证2223### 🟡 中危24- [ ] XSS 风险(未转义的用户输入)25- [ ] CSRF 保护缺失26- [ ] 不安全的随机数生成27- [ ] 敏感信息日志泄露28- [ ] 过宽的权限设置29- [ ] 缺少 Rate Limiting3031### 🟢 低危32- [ ] 缺少输入验证33- [ ] 依赖版本过旧34- [ ] 缺少安全头部(CSP, HSTS, X-Frame-Options)35- [ ] 错误信息泄露内部细节36- [ ] 缺少 HTTPS 强制3738## 输出格式3940```markdown41## 🔒 安全审计报告4243### 审计概览44- 审计范围:xxx45- 发现问题:🔴 高危 X 个 / 🟡 中危 X 个 / 🟢 低危 X 个4647### 🔴 高危问题48#### 1. [文件路径:行号]49- **漏洞类型**:xxx50- **风险描述**:xxx51- **攻击场景**:攻击者可以通过 xxx 方式...52- **修复方案**:53 ```code54 // 修复前55 // 修复后56 ```5758### 🟡 中危问题59...6061### 🟢 低危问题62...6364### 依赖安全65| 依赖名 | 当前版本 | 建议版本 | 风险 |66|--------|---------|---------|------|6768### 修复优先级建议691. 立即修复:...702. 本周修复:...713. 长期改进:...72```7374## 注意事项75- 提供修复前后的代码对比76- 对于每条漏洞,说明具体的攻击向量77- 优先级基于可利用性和影响范围判断
Excerpt shown under the repository's MIT license.
More skills in claude-code-skills-zh
Similar skill repositories
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
The open-source app everyone uses to manage agents at work
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
