/ 目录 / 演练场 / security-skills
← 全部服务器 ↗ GitHub
● 社区 eth0izzle ⚡ 即开即用

security-skills

作者 eth0izzle · eth0izzle/security-skills

Defensive security skills for Claude Code — threat modeling, config review, dependency audits. For blue teams, not pentesters.

A collection of Claude Code skills oriented around defensive security work: reviewing IAM policies, checking dependency trees for known CVEs, producing threat models for new features, auditing Dockerfiles and k8s manifests for common misconfigurations.

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

实时演示

实际使用效果

security-skill.replay ▶ 就绪
0/0

安装

作者仓库 · Claude Skills 官方文档

使用场景

实战用法： security-skills

Produce a STRIDE threat model for a new feature

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

何时使用： Design review for a feature that touches user data, auth, or external networks.

步骤
  1. Walk the system
    Use security-skills. Here's the design for [feature]. Enumerate trust boundaries and data flows.✓ 已复制
    → Named trust boundaries, explicit data flow arrows
  2. Apply STRIDE
    For each boundary, call out Spoofing, Tampering, Repudiation, Info Disclosure, DoS, Elevation risks.✓ 已复制
    → Table with threats scored, not generic 'consider XSS'
  3. Propose mitigations
    Rank the threats by likelihood * impact and propose concrete mitigations for the top 5.✓ 已复制
    → Specific controls (rate limit, signed requests, audit log)

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

注意事项
  • STRIDE becomes checkbox theater — Demand concrete attacker stories — 'attacker with X wants Y, does Z'
搭配使用： filesystem

Sweep a repo's dependencies for known CVEs

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

何时使用： A new CVE drops and you need to know where you're exposed.

步骤
  1. Point at the manifest
    Use security-skills. Audit package-lock.json for dependencies with known CVEs published in the last 90 days.✓ 已复制
    → List of packages, advisory IDs, severity
  2. Triage by usage
    For each vulnerable dep, grep the codebase — is it actually reachable?✓ 已复制
    → Reachable vs unreachable classification
  3. Draft an upgrade plan
    Plan the minimum-risk upgrade order so CI doesn't explode.✓ 已复制
    → Ordered upgrade sequence with version pins

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

注意事项
  • Transitive dependencies missed — Use full lockfile, not just top-level manifest
搭配使用： filesystem · github

Review Terraform and k8s manifests for common misconfigs

👤 Platform engineers, DevSecOps ⏱ ~30 min intermediate

何时使用： Before merging IaC changes into main, or auditing what's already there.

步骤
  1. Point Claude at the IaC directory
    Use security-skills. Scan terraform/ for S3 buckets without encryption, IAM wildcards, public security groups.✓ 已复制
    → File+line references with severity
  2. Get fixes
    For each finding, propose the minimal Terraform diff to fix it.✓ 已复制
    → HCL snippets showing before/after

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

注意事项
  • False positives on intentional public assets — Tag resources that are intentionally public; the skill should skip them
搭配使用： github · filesystem

组合

与其他 MCP 搭配，撬动十倍杠杆

security-skill + github

Post findings as PR comments automatically

Review this PR and leave line comments for each security finding.✓ 已复制
security-skill + filesystem

Recursive scans across a monorepo

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

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
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

成本与限制

运行它的成本

API 配额
None built-in
每次调用 Token 数
Moderate — depends on files inspected
费用
Free
提示
Scope scans to specific directories; don't point at node_modules.

安全

权限、密钥、影响范围

凭据存储： None in skill itself
数据出站： None — skill is prompts; be aware inspected code goes to Claude API

故障排查

常见错误与修复

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.

替代方案

security-skills 对比其他方案

替代方案何时用它替代权衡
Trivy / GrypeYou need an authoritative, up-to-date vulnerability databaseNo LLM reasoning — just raw scan output
tfsec / checkovSpecific IaC scanning with a curated rule setRule-bound; misses nuanced misconfigs

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills