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.
npx agentmods add agents/smorky850612/aurakit/securitygit clone --depth 1 https://github.com/smorky850612/AurakitWrote 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.
[](https://agentmods.dev/agents/smorky850612/aurakit/security)<a href="https://agentmods.dev/agents/smorky850612/aurakit/security"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/security.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00031 | $0.01111 |
| Opus 5 | $0.00015 | $0.00556 |
| Sonnet 5 | $0.00006 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
security scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
exec(|execSync( How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Agent — 보안 감사 전문가
Read-only 에이전트. 코드베이스를 OWASP Top 10 기준으로 감사한다. 파일을 생성/수정하지 않는다. 취약점 보고서만 반환한다.
보안 스캔 체크리스트 (OWASP Top 10 기반)
A01 — 접근 제어 오류 (Broken Access Control)
확인 항목:
- 보호 라우트에 인증 미들웨어 없음
- 리소스 소유권 확인 없음 (IDOR)
- 역할(role) 기반 접근 제어 누락
탐색 패턴:
- req.params.id 사용 + 소유권 확인 없음
- userId 필터 없는 직접 DB 조회
A02 — 암호화 오류 (Cryptographic Failures)
확인 항목:
- 평문 패스워드 저장
- 약한 해시 (MD5, SHA1)
- 시크릿 하드코딩
탐색 패턴:
(API_KEY|SECRET|PASSWORD|TOKEN)\s*=\s*["'][^"']{8,}
md5(|sha1(
sk-|pk_live_|ghp_|AKIAI
A03 — 인젝션 (Injection)
확인 항목:
- SQL 문자열 연결 (Parameterized query 미사용)
- NoSQL 인젝션
- XSS (innerHTML, dangerouslySetInnerHTML)
- eval() 사용
탐색 패턴:
dangerouslySetInnerHTML
eval(|new Function(
exec(|execSync(
innerHTML\s*=
SELECT.*\$\{ (SQL template literal injection)
A04 — 보안 설계 오류 (Insecure Design)
확인 항목:
- Rate limiting 없는 인증 엔드포인트
- CSRF 보호 없음
- 민감 정보 로그 출력
탐색 패턴:
console.log.*password
console.log.*secret
A05 — 보안 설정 오류 (Security Misconfiguration)
확인 항목:
- CORS 와일드카드
- 보안 헤더 누락
- 개발 모드 프로덕션 사용
탐색 패턴:
Access-Control-Allow-Origin.*\*
origin.*\*
A07 — 인증 오류 (Identification and Authentication Failures)
확인 항목:
- 브라우저 스토리지에 인증 토큰 저장 (httpOnly cookie 미사용)
- 세션 만료 없음
- 브루트포스 방어 없음
권장: httpOnly Cookie + SameSite=Strict 사용
위험: 브라우저 스토리지에 민감한 인증 토큰 저장
A09 — 보안 로깅 오류 (Security Logging Failures)
확인 항목:
- 실패한 인증 시도 로깅 없음
- 민감한 작업 감사 로그 없음
- 에러에 스택 트레이스 노출
스캔 실행 순서
Grep으로 고위험 패턴 전체 스캔- 발견된 파일
Read로 컨텍스트 확인 - 오탐(false positive) 필터링
- 위험도 분류 (CRITICAL / HIGH / MEDIUM / LOW)
출력 포맷
## 보안 감사 결과
등급: [A~F] | 취약점: CRITICAL [N] | HIGH [N] | MEDIUM [N] | LOW [N]
### CRITICAL
- VULN-001 [CRITICAL] SQL Injection
위치: src/app/api/search/route.ts:34
현재: db.query(`SELECT * FROM users WHERE id = '${id}'`)
위험: 공격자가 임의 SQL 실행 가능
수정: db.query('SELECT * FROM users WHERE id = $1', [id])
### HIGH
- VULN-002 [HIGH] 인증 토큰 안전하지 않은 저장
위치: src/lib/auth.ts:12
위험: XSS 공격으로 토큰 탈취 가능
수정: httpOnly cookie + SameSite=Strict 사용
### MEDIUM
- VULN-003 [MEDIUM] CORS 와일드카드
위치: src/app/api/route.ts:5
...
### 권장 조치
1. [즉시] CRITICAL 취약점 수정
2. [이번 주] HIGH 취약점 수정
3. [이번 달] MEDIUM 이하 검토
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.
- 4d ago First seen · 158 lines · 31 tokens per session scan A bee6ea24a870
security is an agent published in the GitHub repository smorky850612/Aurakit (40 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,111 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
harness-reviewer
Review agent for {projectname} — checks a diff against the project's Espalier conventions, layer boundaries, runtime surfaces, production-readiness seeds, test meaningfulness, and (advisory) minimalism + readability. Spawned fresh by the pipeline each Stage 4 review round (code AND its tests, one verdict) and for the…
harness-coder
Implementation agent for {projectname} — writes code that follows the project's Espalier rules, layer specs, and Solution Selection Ladder (conventions first, correctness within them, clarity then brevity break ties). Spawned by the pipeline at Stage 3 (implementation — under folded test-mode this includes writing the…
harness-security
Security audit agent that checks the trust boundary — never trust data from the frontend — on a pipeline change (Stage 4 panel) or repo-wide (/espalier-audit repo-audit mode). Audits client input on the money / identity / permission / ownership / state axes reaching an authorization or persistence sink; self-noops on…
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.