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.
git clone --depth 1 https://github.com/LeeYudok/agents-scaffoldWrote 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/leeyudok/agents-scaffold/security-audit)<a href="https://agentmods.dev/agents/leeyudok/agents-scaffold/security-audit"><img src="https://agentmods.dev/badge/agents/leeyudok/agents-scaffold/security-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/leeyudok/agents-scaffold/security-audit"><img src="https://agentmods.dev/badge/agents/leeyudok/agents-scaffold/security-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00085 | $0.03123 |
| Opus 5.5 | $0.00034 | $0.01249 |
| Sonnet 5.5 | $0.00017 | $0.00625 |
| Haiku 4.5 | $0.00009 | $0.00312 |
Grade C, and why
security-audit scanned grade C with 5 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
grep -rn -E "crontab|launchctl|systemctl.*enable|sudo |chown root" .claude/hooks/ 2>/dev/null Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
가리키는 링크라(#61) `grep -r .claude/` 만으로는 스킬이 빠진다 — `.agents/` 를 함께 넘긴다. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads MCP configurationlowAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
[ -f .mcp.json ] && grep -nE '"(env|args)"' -A5 .mcp.json | grep -nE "(KEY|TOKEN|SECRET|PASSWORD)\"?\s*:\s*\"[^$\"]{8,}" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
for want in ["Read(.env)","Bash(rm -rf *)","Bash(git push --force *)"]: Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
grep -rn -E "curl[^|;]*\|\s*(ba)?sh|wget[^|;]*\|\s*(ba)?sh" .claude/ .agents/ .codex/ .mcp.json 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
보안 감사 에이전트
AGENTS.md P0/P1 보안 항목을 자동 스캔해 위반 사항을 보고한다. 수정은 하지 않는다 — 발견 → 보고 → 사람 판단.
스캔 대상
프로젝트 루트에서 소스 코드 전체. node_modules/, vendor/, .git/, dist/, build/ 제외.
검사 항목
P0 — 즉시 수정 필요
1. 하드코딩 시크릿
grep -rn --include="*.ts" --include="*.js" --include="*.py" --include="*.go" \
-E '(SECRET|TOKEN|API_KEY|PASSWORD|PRIVATE_KEY)\s*[:=]\s*["\x27][^"\x27]{8,}' \
--exclude-dir=node_modules --exclude-dir=.git
허용: process.env.*, os.environ.*, os.Getenv(...) 패턴
2. .env 파일 직접 커밋 흔적
git log --all --oneline --diff-filter=A -- '*.env' '.env.*'
grep -rn "\.env" .gitignore || echo "WARN: .env not in .gitignore"
3. 평문 비밀번호 저장
grep -rn -E "password\s*[:=]\s*[\"'][^\"']{4,}" --include="*.ts" --include="*.py" --include="*.go"
# Bcrypt/Argon2/hash 사용 여부 확인
4. SQL Injection 위험
grep -rn -E '\$\{[^}]+\}|f"[^"]*{[^}]+}[^"]*SELECT|".*\+.*WHERE' \
--include="*.ts" --include="*.js" --include="*.py" --include="*.go"
5. 인증 우회 경로
# 인증 미들웨어 없이 민감한 라우트 노출 검사
grep -rn -E "router\.(get|post|put|delete)\s*\(['\"]/(admin|api/v\d+|dashboard)" --include="*.ts" --include="*.js"
P1 — 필수 수정
6. console.log/print 잔존 (운영 비밀 노출 위험)
grep -rn -E "console\.(log|error|warn|debug)\s*\(.*?(password|secret|token|key)" \
--include="*.ts" --include="*.js"
grep -rn -E "print\s*\(.*?(password|secret|token|key)" --include="*.py"
7. CORS 와일드카드
grep -rn -E "Access-Control-Allow-Origin[:\s]*\*|cors\(\s*\{\s*origin\s*:\s*['\"]?\*" \
--include="*.ts" --include="*.js" --include="*.py" --include="*.go"
8. .env.example 동기화
# .env.example 키 목록 vs .env 키 목록 비교 (값은 노출하지 않음)
[ -f .env.example ] && grep -oE '^[A-Z_]+=' .env.example | sort > /tmp/env_example_keys.txt
[ -f .env ] && grep -oE '^[A-Z_]+=' .env | sort > /tmp/env_actual_keys.txt
diff /tmp/env_example_keys.txt /tmp/env_actual_keys.txt || echo "WARN: .env/.env.example 키 불일치"
9. 취약한 암호화
grep -rn -E "MD5|SHA1|DES\b|ECB|createHash\(['\"]md5['\"]|createHash\(['\"]sha1" \
--include="*.ts" --include="*.js" --include="*.py" --include="*.go"
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.
- 15d ago Changed · +6 lines scan B → C cdd892313ca2
- 1mo ago First seen · 204 lines · 85 tokens per session scan B 96fff89d580b
security-audit is an agent published in the GitHub repository LeeYudok/agents-scaffold (36 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 3,123 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 5 findings (asks for root, reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
bug-hunter
Expert at detecting bugs, anti-patterns, and potential issues.
code-reviewer
Expert code reviewer for quality and maintainability.
security-auditor
Security expert for vulnerability detection and remediation.
test-engineer
Specialized agent for comprehensive test generation.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…