From aims-toolkit
보안, 보안 리뷰, 보안 검토, 취약점, 보안 분석, OWASP, 인증, 인가, 취약점 점검 - Systematic security analysis based on OWASP Top 10. Reviews code for vulnerabilities, designs auth/authz systems, and produces severity-classified reports. Use when auditing security, designing authentication, or pre-deployment security checks. Do NOT use for general code quality reviews (use code-reviewer) or debugging (use debug-specialist).
npx claudepluginhub aimskr/aims-claude-toolkit --plugin aims-toolkitThis skill uses the workspace's default tool permissions.
Systematic workflow for security review and vulnerability analysis.
Audits code security using STRIDE threat modeling, attack trees, CVSS severity ranking, OWASP patterns, and CWE analysis for vulnerabilities in auth, inputs, crypto, and dependencies.
Guides security reviews and vulnerability assessments using OWASP Top 10 checklist and workflow. Use for audits, secure coding reviews, threat modeling, and risk analysis.
Audits code for vulnerabilities using OWASP checklist on injection, authentication, authorization, secrets, input validation, configuration, dependencies, and cryptography risks.
Share bugs, ideas, or general feedback.
Systematic workflow for security review and vulnerability analysis.
Codebase Analysis:
Attack Surface Definition:
Perform systematic check against OWASP Top 10 (2021):
For detailed checklist, code patterns, and search queries:
Read OWASP-CHECKLIST.md in this skill directory.
Severity Classification:
| Level | Description | Response Time |
|---|---|---|
| 🔴 Critical | Immediately exploitable, severe impact | Within 24h |
| 🟠 High | Exploitable, significant impact | Within 1 week |
| 🟡 Medium | Conditional exploit, limited impact | Within 1 month |
| 🟢 Low | Hard to exploit, minimal impact | Next release |
Provide recommendations for:
For OWASP checklist, vulnerable code patterns, search queries, and report templates:
Read OWASP-CHECKLIST.md in this skill directory.
취약점 리포트(Severity 분류 + 권고 사항)가 전달되면 완료.
Too many findings to prioritize: Focus on Critical/High first. If >20 Critical findings, the codebase likely needs a dedicated security sprint rather than a review.
False positives from pattern matching: Verify each finding with actual data flow analysis. A SQL query using parameterized binding is safe even if grep finds SELECT near user input.
Team pushes back on security fixes: Quantify risk with severity + exploitability. "This allows unauthenticated admin access" is more actionable than "A01 violation found."