reviewing-security
OWASP Top 10-based security review and vulnerability detection. Triggers: セキュリティ, 脆弱性, XSS, SQL injection, SQLインジェクション, CSRF, 認証, 認可, 暗号化, OWASP, SSRF, パスワード, セッション, rate limiting, brute force, command injection, security misconfiguration.
When & Why to Use This Skill
This Claude skill automates security audits by performing OWASP Top 10-based reviews and vulnerability detection. It identifies critical security flaws such as SQL injection, Cross-Site Scripting (XSS), and broken access control, providing actionable fix recommendations and exploit scenarios to ensure robust and secure software development.
Use Cases
- Automated Security Auditing: Scanning source code during the development lifecycle to identify vulnerabilities like SQL injection, XSS, and SSRF based on OWASP standards.
- Vulnerability Remediation: Providing developers with specific code patterns and fix recommendations for security misconfigurations, such as insecure CORS policies or plaintext password storage.
- Compliance Checking: Ensuring codebases adhere to security best practices for authentication, authorization, and cryptographic implementations to meet industry safety requirements.
| name | reviewing-security |
|---|---|
| description | > |
| allowed-tools | [Read, Grep, Glob, Task] |
| agent | security-reviewer |
| context | fork |
| user-invocable | false |
Security Review
Detection (OWASP Top 10)
| ID | Category | Pattern | Fix |
|---|---|---|---|
| A01 | Broken Access Control | Missing auth, IDOR, path traversal | Auth middleware, ownership check |
| A02 | Cryptographic Failures | password: 'plaintext' |
bcrypt/argon2 hashing |
| A03 | Injection | db.query(\SELECT...${id}`)` |
Parameterized query, ORM |
| A03 | Injection | exec(\ping ${host}`)` |
Input validation, library instead |
| A03 | XSS | dangerouslySetInnerHTML={{ __html }} |
Default escaping, DOMPurify |
| A05 | Security Misconfiguration | cors({ origin: '*' }) |
Explicit origin allowlist |
| A05 | Security Misconfiguration | cookie: {} (no options) |
secure, httpOnly, sameSite: 'strict' |
| A09 | Logging Failures | logger.info({ password }) |
Exclude sensitive fields |
| A10 | SSRF | fetch(userInputUrl) |
URL validation, allowlist |
Confidence Threshold
Report only when confidence >80%. Include: file:line, exploit scenario, fix recommendation.
References
| Topic | OWASP | File |
|---|---|---|
| Basic | A01, A02, A07 | references/owasp-basic.md |
| Injection | A03 | references/owasp-injection.md |
| Advanced | A04-A06, A08-A10 | references/owasp-advanced.md |