security-audit

Code Security Audit

Trigger Conditions

Activate this skill when the user requests a security check, vulnerability scan, security audit, or dependency security check.

Workflow

1. Determine audit scope — Analyze based on the directory/files/code snippet specified by the user
2. Static security scan — Check item by item according to the checklist
3. Dependency security check — Check dependency files such as package.json / requirements.txt / go.mod
4. Generate audit report — Output classified by severity

Checklist

🔴 High Risk

• Hardcoded keys/passwords/API Keys
• SQL injection risk (string-concatenated SQL)
• Command injection (unfiltered shell commands)
• Path traversal (unvalidated file paths)
• Deserialization vulnerabilities
• Unvalidated JWT/Token verification

🟡 Medium Risk

• XSS risk (unescaped user input)
• Missing CSRF protection
• Insecure random number generation
• Sensitive information leakage in logs
• Overly broad permission settings
• Missing Rate Limiting

🟢 Low Risk

• Missing input validation
• Outdated dependency versions
• Missing security headers (CSP, HSTS, X-Frame-Options)
• Error messages leaking internal details
• Missing HTTPS enforcement

Output Format

## 🔒 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

🟡 Medium-Risk Issues

...

🟢 Low-Risk Issues

...

Dependency Security

Dependency Name	Current Version	Recommended Version	Risk

Remediation Priority Recommendations

1. Fix immediately: ...
2. Fix this week: ...
3. Long-term improvements: ...

## 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