Agent skill
security-review-skill
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/security-review-skill
SKILL.md
Security Review Skill
=== PURPOSE ===
This skill provides procedures for conducting security code reviews. Security Lead has BLOCKING authority for security issues.
=== USED BY ===
| Agent | Purpose |
|---|---|
| @agent(security-lead) @ref(CB-AGENT-SECURITY-001) | Primary skill for security reviews |
=== PROCEDURE: Security Review Checklist ===
Template: @ref(CB-TPL-SECREVIEW-001)
Authentication
- Authentication required for protected routes
- Session management is secure
- Password policies enforced
- MFA implemented where required
Authorization
- Authorization checks on all endpoints
- Role-based access control implemented
- Principle of least privilege followed
- No privilege escalation possible
Input Validation
- All inputs validated and sanitized
- SQL injection prevented (parameterized queries)
- XSS prevented (output encoding)
- Command injection prevented
- Path traversal prevented
Data Protection
- Sensitive data encrypted at rest
- Sensitive data encrypted in transit
- PII handled appropriately
- No secrets in code or logs
Error Handling
- Errors don't expose sensitive info
- Stack traces not exposed to users
- Errors logged appropriately
Dependencies
- No known vulnerable dependencies
- Dependencies from trusted sources
- Dependency versions pinned
=== PROCEDURE: OWASP Top 10 Check ===
Review against OWASP Top 10:
- Broken Access Control
- Cryptographic Failures
- Injection
- Insecure Design
- Security Misconfiguration
- Vulnerable Components
- Authentication Failures
- Data Integrity Failures
- Logging Failures
- SSRF
=== PROCEDURE: Security Finding Documentation ===
Format:
### [SEVERITY] Finding Title
**Location:** file.js:line
**Type:** [Injection/XSS/Auth/etc.]
**Severity:** [Critical/High/Medium/Low]
**Description:**
What the vulnerability is.
**Impact:**
What could happen if exploited.
**Recommendation:**
How to fix it.
**References:**
- [CWE-XXX](link)
=== SEVERITY DEFINITIONS ===
| Severity | Definition | Action |
|---|---|---|
| Critical | Immediate exploitation risk | Block, fix immediately |
| High | Significant security risk | Block, fix before merge |
| Medium | Moderate risk | Block, create issue |
| Low | Minor issue | Advisory, create issue |
=== ANTI-PATTERNS ===
Rubber Stamp Reviews
Problem: Approving without thorough review Solution: Follow checklist, document findings
Missing Context
Problem: Reviewing code without understanding flow Solution: Understand authentication/authorization context
=== RELATED SKILLS ===
| Skill | Relationship |
|---|---|
| @skill(vulnerability-assessment) | Broader vulnerability context |
| @skill(compliance-check) | Compliance implications |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?