인터페이스는 현지화되어 있으며, Skill 소개와 설명 문서는 선택한 언어로 AI가 자동 번역합니다. 코드·명령어·경로·전문 용어는 원문을 유지하며 원작자 문서가 우선합니다.
Skills 둘러보기
데이터 및 연구 · SKILL.md

security-audit

security-audit

Deep security audit covering OWASP Top 10, authentication, authorization, data protection, dependency vulnerabilities, and secrets scanning. Delegates to the Centinela (QA) agent.

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill 문서

GitHub

name: security-audit category: quality-security description: Deep security audit covering OWASP Top 10, authentication, authorization, data protection, dependency vulnerabilities, and secrets scanning. Delegates to the Centinela (QA) agent.

Security Audit

Performs a deep security audit using the Centinela (QA) agent.

When to Use This Skill

  • Before a release to verify security posture
  • After significant code changes that touch authentication, authorization, or data handling
  • Periodic security review of the codebase
  • When adding new dependencies or external integrations

What This Skill Does

  1. Runs the SIGN IN checklist
  2. Performs OWASP Top 10 systematic check (A01-A10)
  3. Scans for hardcoded secrets, API keys, tokens, and connection strings
  4. Audits dependencies for known CVEs
  5. Checks smart contracts if Solidity is present (reentrancy, overflow, access control)
  6. Runs Security Verification and Quality Verification checklists (TIME OUT)
  7. Issues verdict and writes report to docs/reviews/security-audit-{date}.md
  8. Prepares findings handoff to Dev agent

How to Use

Basic Usage

/security-audit

Scoped Audit

/security-audit src/auth/ src/api/

Example

User: /security-audit src/payments/

Output: A security audit report at docs/reviews/security-audit-2026-02-23.md with:

  • OWASP Top 10 findings organized by severity
  • Secrets scan results
  • Dependency vulnerability report
  • Verdict: APPROVED or CHANGES REQUIRED
  • Fix order recommendation for the Dev agent

Tips

  • If no scope is specified, the entire src/ directory is audited
  • Critical findings trigger the Non-Normal emergency checklist
  • The agent will never attempt to fix vulnerabilities — only document them
저장한 Skills