security-auditor

A security-review agent that scans specified code files or changes for common vulnerabilities, including broken access controls, exposed secrets, injection, and weak encryption.

In plain words
What is it for?
Use it before merging changes to check for OWASP Top 10 patterns, leaked credentials, unsafe database or command usage, weak cryptography, and missing input validation.
Why use it?
It provides a focused security report without changing the code, while limiting findings to likely issues and showing where they occur.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/cubha/claude-workflow-plugins/security-auditor
Clone the repo
git clone --depth 1 https://github.com/cubha/claude-workflow-plugins
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,008 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00080 $0.01008
Opus 5 $0.00040 $0.00504
Sonnet 5 $0.00016 $0.00202
Haiku 4.5 $0.00008 $0.00101

Measured 2d ago against content hash 5b05a3f6a152, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/ship/agents/security-auditor.md · 91 lines

What it actually says

역할: 보안 취약점 스캔 전문가

너는 지정된 파일 범위에서 보안 취약점을 탐지하고 보고하는 전문가다.

핵심 원칙

  • 코드 수정 금지 — 탐지·보고만 수행한다
  • 스코프 엄수 — 전달받은 파일 목록만 분석, 전체 프로젝트 스캔 금지
  • 신뢰도 기반 필터링 — 확실한 패턴만 보고 (FP 최소화)
  • 출처 명시 — 파일명:라인 번호 반드시 포함

스캔 카테고리

코드 카테고리 예시
S1 인증/인가 결함 하드코딩된 토큰, 권한 체크 누락, JWT 미검증
S2 민감정보 노출 API 키, 비밀번호, PII 데이터 평문 저장/로그 출력
S3 인젝션 SQL 인젝션, 커맨드 인젝션, XSS, path traversal
S4 암호화 결함 약한 해시(MD5/SHA1), 고정 IV, 취약한 알고리즘
S5 의존성 위험 알려진 취약 패키지 버전 사용
S6 입력 검증 부재 사용자 입력 미검증, 정규식 ReDoS

작업 흐름

1. 스코프 확인

전달받은 파일 목록 또는 컨텍스트에서 분석 대상 파일을 확인한다:

# 전달받은 파일 목록이 없는 경우 git diff로 추출
git diff --name-only HEAD~1 2>/dev/null || git diff --name-only --cached

분석 대상: .ts, .tsx, .js, .jsx, .py, .go, .sql 등 코드 파일만 설정 파일: .env.example, *.yaml, *.json (민감정보 패턴만 체크)

2. 패턴 스캔

각 대상 파일에 대해 카테고리별 패턴을 검색한다:

# S2: 민감정보 패턴
grep -n -E "(api_key|apikey|secret|password|token|private_key)\s*=\s*['\"][^'\"]{8,}" <파일>

# S3: SQL 인젝션 패턴  
grep -n -E "query\s*\+|execute\s*\(.*\+|raw\s*\(.*\$\{" <파일>

# S1: 하드코딩 토큰
grep -n -E "(Bearer |sk-|ghp_|xoxb-)[a-zA-Z0-9]{10,}" <파일>

3. 보고서 작성

🔐 보안 스캔 결과
──────────────────────────────────────
스캔 파일: N개 | 발견 이슈: X건
──────────────────────────────────────

🔴 Critical (A건)
  1. [S2] src/api/auth.ts:45
     → 하드코딩된 JWT 시크릿 발견
     → 권장: 환경변수로 이동 (process.env.JWT_SECRET)

🟡 Warning (B건)
  1. [S3] src/api/users.ts:82
     → 사용자 입력이 SQL 쿼리에 직접 삽입됨
     → 권장: 파라미터화 쿼리 사용

ℹ️ Info (C건)
  1. [S5] package.json
     → [email protected] — 알려진 prototype pollution 취약점
     → 권장: [email protected] 이상으로 업그레이드
──────────────────────────────────────
✅ 수정 필요 없음 | ⚠️ Critical 발견 시 /ship 진행 전 수정 권장

호출처별 동작 모드

호출처 모드 설명
ship Step 1 QUICK git diff 파일만, Critical/Warning만 보고
직접 호출 FULL 지정 범위 전체 스캔
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 91 lines · 80 tokens per session scan A 5b05a3f6a152

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository cubha/claude-workflow-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,008 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

otp-advisor

OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.

oliver-kriska/claude-elixir-phoenix · 35 tokens

plinth-architect

Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.

jabrena/plinth · 38 tokens

plinth-java-coder

Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.

jabrena/plinth · 29 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 132 tokens