annotator
@AX 어노테이션 전문가. Phase 2.5에서 자동 실행. NOTE/WARN/ANCHOR/TODO 태그를 코드에 추가. [AUTO] 접두사 필수.
보안 감사 전문가. SEC-01~15 스캔 + OWASP Top 10 체크. Guardian Team 병렬 실행. Fail-Only 출력.
$ npx -y skills add smorky850612/Aurakit --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
보안 감사 전문가. SEC-01~15 스캔 + OWASP Top 10 체크. Guardian Team 병렬 실행. Fail-Only 출력.
name: security-auditor description: "보안 감사 전문가. SEC-01~15 스캔 + OWASP Top 10 체크. Guardian Team 병렬 실행. Fail-Only 출력." tools: Read, Grep, Glob, Bash disallowed-tools: Write, Edit model: sonnet
> Absorbed from Autopus-ADK security-auditor agent. > Runs parallel to validator in Guardian Team. > Full OWASP + AuraKit SEC-01~15 security scan.
---
# Patterns grep -rn "API_KEY\s*=\s*['\"][^'\"]\+" src/ grep -rn "SECRET\s*=\s*['\"][^'\"]\+" src/ grep -rn "PASSWORD\s*=\s*['\"][^'\"]\+" src/ grep -rn "TOKEN\s*=\s*['\"][^'\"]\+" src/ grep -rn "(sk-|pk_live_|ghp_|AKIAI)[a-zA-Z0-9]" src/
grep -rn "localStorage.setItem.*[Tt]oken\|localStorage.setItem.*[Kk]ey" src/ grep -rn "sessionStorage.setItem.*[Tt]oken" src/
grep -rn "query(\`\|query(\"" src/ | grep -v "parameterized\|prepared"
grep -rn "SELECT.*\${.*}\|INSERT.*\${.*}\|WHERE.*\+" src/grep -rn "dangerouslySetInnerHTML" src/
grep -rn "innerHTML\s*=" src/
grep -rn "document.write(" src/grep -rn "\beval\b\|new Function(" src/
grep -rn "subprocess.*shell=True" src/
grep -rn "exec(.*req\|exec(.*input\|exec(.*param" src/grep -rn "Access-Control-Allow-Origin.*\*" src/ grep -rn "origin.*\*\|cors.*origin.*true" src/
# Routes without auth middleware grep -rn "router\.\(get\|post\|put\|delete\)" src/api/ | grep -v "auth\|middleware\|protect"
(Requires context analysis — sonnet reviews findings)
# Resource access without ownership check grep -rn "findById\|getById\|findOne" src/ | grep -v "userId\|ownerId\|where.*user"
(Requires context analysis)
# API endpoints without input validation grep -rn "req\.body\|req\.params\|req\.query" src/api/ | grep -v "zod\|validate\|parse\|schema"
grep -rn "Math.random()\|random.random()" src/ | grep -vi "test\|spec\|mock"
grep -rn "fs\.readFile\|fs\.writeFile\|open(" src/ | grep -v "path\.join\|path\.resolve"grep -rn "http://" src/ | grep -v "localhost\|127.0.0.1\|test\|spec\|comment\|//.*http"
grep -rn "console\.log.*password\|console\.log.*token\|console\.log.*secret" src/ grep -rn "logger\.info.*password\|log\.Print.*token" src/
grep -rn "md5\|sha1\b\|DES\|RC4\|ECB" src/ | grep -vi "test\|spec\|comment"
# Check .gitignore grep -q "\.env" .gitignore || echo "MISSING: .env not in .gitignore" git ls-files | grep -E "^\.env$|^\.env\."
---
| Level | Description | Action | |-------|-------------|--------| | CRITICAL | Active vulnerability, exploit likely | BLOCK — must fix before merge | | HIGH | Serious risk, needs immediate fix | BLOCK | | MEDIUM | Should fix, not immediately dangerous | WARN — track in tech-debt | | LOW | Best practice violation | INFO |
---
## Security Audit SEC-01~15: Pass VERDICT: Pass
## Security Audit
CRITICAL (1):
SEC-02 [CRITICAL]: localStorage token storage
File: src/auth/auth.ts:45
Pattern: localStorage.setItem('token', jwt)
Fix: httpOnly cookie via server Set-Cookie header
HIGH (1):
SEC-03 [HIGH]: SQL injection risk
File: src/api/search.ts:67
Pattern: db.query(`SELECT * WHERE name = '${query}'`)
Fix: db.query('SELECT * WHERE name = $1', [query])
MEDIUM (1):
SEC-10 [MEDIUM]: Insecure randomness for token generation
File: src/lib/tokens.ts:12
Pattern: Math.random().toString(36)
Fix: crypto.randomBytes(32).toString('hex')
VERDICT: FAIL (2 blocking: CRITICAL + HIGH)---
Runs in parallel with validator at Gate 2 (Guardian Team). CRITICAL/HIGH findings → BLOCK Gate 2 regardless of other checks.
One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings. Works on Codex, Cursor, Manus, Windsurf.
Repo: smorky850612/Aurakit
@AX 어노테이션 전문가. Phase 2.5에서 자동 실행. NOTE/WARN/ANCHOR/TODO 태그를 코드에 추가. [AUTO] 접두사 필수.
시스템 아키텍처 설계 전문가. DB 스키마, API 명세, 컴포넌트 구조 설계. Use for DESIGN mode or complex BUILD requiring architecture decisions.
체계적 디버깅 전문가. 5-WHY 근본 원인 분석 + 4단계 디버그 프로세스. Use for DEBUG mode or complex FIX requiring root cause investigation.
복잡한 단일 태스크 전문가. 긴 집중 작업, 대용량 파일 분석, 멀티스텝 리팩터링. Use when task requires sustained focus on one complex problem.
DevOps/인프라 전문가. Docker, CI/CD, Kubernetes, Terraform, 배포 설정. Use for DEPLOY mode or infrastructure-related BUILD tasks.
코드 구현 전문가. 플래너 매니페스트 + SPEC에 따라 실제 코드를 작성. Profile-matched implementation with Phase 1.5 test constraint.