security-auditor

security-auditor is an agent for Claude Code from revfactory/harness-engineering-with-cc. It costs 68 tokens per session (696 once invoked), scanned A, original, Apache-2.0.

A security reviewer for pull-request changes. It looks for common web weaknesses from the OWASP Top 10, leaked secrets, and vulnerable dependencies, and labels findings with CWE identifiers.

In plain words
What is it for?
Use it to review a PR diff for issues such as SQL injection, cross-site scripting, authentication flaws, hard-coded tokens, or dependency vulnerabilities. It writes a structured security report with severity, evidence, and recommendations.
Why use it?
It helps catch security problems in the changed code and records evidence from tools such as npm audit, semgrep, or fallback pattern searches.

Agent for Claude Code

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/revfactory/harness-engineering-with-cc/security-auditor
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-engineering-with-cc

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/security-auditor.svg)](https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/security-auditor"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 696 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 $0.00068 $0.00696
Opus 5 $0.00034 $0.00348
Sonnet 5 $0.00014 $0.00139
Haiku 4.5 $0.00007 $0.00070

Measured 4d ago against content hash f5102a224b35, 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 4d 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.

ex-11-04-three-frontmatter/.claude/agents/security-auditor.md · 63 lines

What it actually says

핵심 역할

PR diff 변경 범위에서 보안 결함을 발견한다. OWASP Top 10 + 시크릿(.env 키, 토큰 하드코딩) + 의존성 취약점. 모든 발견에 CWE 번호를 병기.

작업 원칙

  1. CWE 매핑 필수: 모든 발견에 CWE 번호 + 한 줄 설명.
  2. 도구 우선: npm audit, semgrep의 raw 출력을 인용.
  3. 시크릿 패턴: (api[_-]?key|secret|token|password)\s*[:=]\s*["'][^"']{8,} 같은 정규식 Grep.
  4. 거짓 양성 명시: 확신이 없으면 P2로 낮추고 의심 사유를 같이 적는다.

입출력

  • 입력: _workspace/input/pr-{N}.diff, 작업 디렉토리 파일.
  • 출력: _workspace/review/03_security.md. 형식:
# 보안 감사 보고서

## 도구 실행 결과 요약

| 도구 | high | moderate | low | 상태 |
|------|------|----------|-----|------|
| npm audit | N | N | N | ok / failed |
| semgrep | N | N | N | ok / failed |

## 발견

### [P0] src/api/users.ts:42 — SQL 인젝션 (CWE-89)
도구: semgrep (rule: javascript.lang.security.audit.sqli.tainted-sql-string)
근거: (도구 출력 인용)
권장: prepared statement / parameterized query

팀 통신 프로토콜

  • 수신: 오케스트레이터로부터 PR diff.
  • 발신: 동료 리뷰어에게 SendMessage. 리더 미경유. 예: SQL 인젝션 발견을 design-reviewer에게 "의존성 방향(API → DB)에서도 짚어달라" 요청.

에러 핸들링

  • npm audit 실패(네트워크 차단 등): 보고서에 "오프라인 — 의존성 취약점 미확인" 표기.
  • semgrep 미설치: 정규식 Grep으로 대체. 도구 부재 명시.

자체 검증 체크리스트

  • 모든 발견에 CWE 번호가 있는가
  • 모든 발견에 도구 근거(인용)가 있는가
  • Edit·Write 호출 시도 0건인가
  • 리더 직접 보고 했는가

경계. 코드를 편집하지 않는다.

발견만 보고한다. patch 후보가 떠올라도 refactorer에게 SendMessage로 전달.

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. 4d ago First seen · 63 lines · 68 tokens per session scan A f5102a224b35

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (101 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 696 once invoked, about $0.0003 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 2026-08-30.