security-skills MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Threat modeling template based on STRIDE
Dependency CVE cross-referencing workflow
IaC misconfiguration checks (Terraform, Docker, k8s)
Security code review patterns
Defensive focus — no exploitation tooling

라이브 데모

실제 사용 모습

security-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "security-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/eth0izzle/security-skills",
        "~/.claude/skills/security-skills"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "security-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/eth0izzle/security-skills",
        "~/.claude/skills/security-skills"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "security-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/eth0izzle/security-skills",
        "~/.claude/skills/security-skills"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "security-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/eth0izzle/security-skills",
        "~/.claude/skills/security-skills"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "security-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/eth0izzle/security-skills",
        "~/.claude/skills/security-skills"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "security-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/eth0izzle/security-skills",
          "~/.claude/skills/security-skills"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add security-skill -- git clone https://github.com/eth0izzle/security-skills ~/.claude/skills/security-skills

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: security-skills

Produce a STRIDE threat model for a new feature

👤 Security engineers, staff+ engineers owning a feature's security review ⏱ ~45 min advanced

언제 쓸까: Design review for a feature that touches user data, auth, or external networks.

사전 조건

Feature design doc or architecture diagram — Paste into chat or point Claude at the file
Skill installed — git clone https://github.com/eth0izzle/security-skills ~/.claude/skills/security-skills

흐름

Walk the system

Use security-skills. Here's the design for [feature]. Enumerate trust boundaries and data flows.✓ 복사됨

→ Named trust boundaries, explicit data flow arrows
Apply STRIDE

For each boundary, call out Spoofing, Tampering, Repudiation, Info Disclosure, DoS, Elevation risks.✓ 복사됨

→ Table with threats scored, not generic 'consider XSS'
Propose mitigations

Rank the threats by likelihood * impact and propose concrete mitigations for the top 5.✓ 복사됨

→ Specific controls (rate limit, signed requests, audit log)

결과: A threat model doc ready for a security review meeting.

함정

STRIDE becomes checkbox theater — Demand concrete attacker stories — 'attacker with X wants Y, does Z'

함께 쓰기: filesystem

Sweep a repo's dependencies for known CVEs

👤 Dev teams responding to a security advisory ⏱ ~30 min intermediate

언제 쓸까: A new CVE drops and you need to know where you're exposed.

흐름

Point at the manifest

Use security-skills. Audit package-lock.json for dependencies with known CVEs published in the last 90 days.✓ 복사됨

→ List of packages, advisory IDs, severity
Triage by usage

For each vulnerable dep, grep the codebase — is it actually reachable?✓ 복사됨

→ Reachable vs unreachable classification
Draft an upgrade plan

Plan the minimum-risk upgrade order so CI doesn't explode.✓ 복사됨

→ Ordered upgrade sequence with version pins

결과: A concrete patch plan — not 'run npm audit fix' and pray.

함정

Transitive dependencies missed — Use full lockfile, not just top-level manifest

함께 쓰기: filesystem · github

Review Terraform and k8s manifests for common misconfigs

👤 Platform engineers, DevSecOps ⏱ ~30 min intermediate

언제 쓸까: Before merging IaC changes into main, or auditing what's already there.

흐름

Point Claude at the IaC directory

Use security-skills. Scan terraform/ for S3 buckets without encryption, IAM wildcards, public security groups.✓ 복사됨

→ File+line references with severity
Get fixes

For each finding, propose the minimal Terraform diff to fix it.✓ 복사됨

→ HCL snippets showing before/after

결과: PR-sized security fixes you can merge incrementally.

함정

False positives on intentional public assets — Tag resources that are intentionally public; the skill should skip them

함께 쓰기: github · filesystem

조합

다른 MCP와 조합해 10배 효율

security-skill + github

Post findings as PR comments automatically

Review this PR and leave line comments for each security finding.✓ 복사됨

security-skill + filesystem

Recursive scans across a monorepo

Walk the entire services/ tree and aggregate findings by service.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
threat_model	system description	Design-phase review	0
cve_audit	lockfile path	After a public CVE drops	0 (uses public advisory data)
iac_review	directory path	Pre-merge IaC audits	0
secret_scan	path or diff	Pre-commit or pre-push	0

비용 및 제한

운영 비용

API 쿼터: None built-in
호출당 토큰: Moderate — depends on files inspected
금액: Free
팁: Scope scans to specific directories; don't point at node_modules.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None in skill itself

데이터 외부 송신: None — skill is prompts; be aware inspected code goes to Claude API

Defensive only. Do not use for exploitation, credential harvesting, or red-team operations.
Never paste production secrets into prompts — even when asking the skill to 'find them'.

문제 해결

자주 발생하는 오류와 해결

Skill suggests exploitation techniques

Re-prompt for defensive framing: 'as a defender, how do I prevent X'

Too many false positives on IaC scan

Provide context (prod vs staging; intentional public resources)

Missed a known vulnerability

Claude's knowledge cutoff may lag. Pair with a proper scanner (Trivy, Snyk) for authoritative CVE data.

대안

security-skills 다른 것과 비교

대안	언제 쓰나	단점/장점
Trivy / Grype	You need an authoritative, up-to-date vulnerability database	No LLM reasoning — just raw scan output
tfsec / checkov	Specific IaC scanning with a curated rule set	Rule-bound; misses nuanced misconfigs

security-skills