Claude Security Skills MCP Server by GoldenWing-360

<p align="center"> <img src="./assets/banner.png" alt="Claude Code Security Skills" width="100%"> </p> <div align="center">

Claude Code Security Skills

Defensive security playbooks for LLM coding agents and the developers using them

38 production-tested skills · 13 security domains · defensive-only · MIT-licensed

Get started · What's inside · Find a skill · Read on dev.to · Read on goldenwing.at · Contributing

</div>

---

⚠️ Independent project — Not affiliated with Anthropic PBC. The skills are plain Markdown with YAML frontmatter and work with any LLM coding agent that supports the same convention.

Give any LLM coding agent the instincts of a senior engineer

A senior engineer knows when a --no-verify flag is hiding a real bug, when an empty catch {} is silently swallowing an auth check, what to do when a customer's WordPress site starts redirecting to a casino, and how to harden a fresh VPS in thirty minutes. Your AI coding agent doesn't — unless you give it these skills.

This repo contains 38 production-tested defensive security skills, each a self-contained Markdown file with YAML frontmatter so Claude Code (or any compatible agent) can auto-trigger the right one. Every skill comes from real incident-response, hardening, and audit work — generalized so the patterns travel beyond the original engagement. Clone it, point your agent at it, and your next deploy, audit, or 3am alert gets expert-level guidance in seconds.

What's inside — 13 security domains

Domain	Skills	What it covers
🤖 AI & LLM security	6	MCP security · agent guardrails · prompt injection defense · OWASP LLM Top 10 · coding-agent failure modes · RAG pipelines
🌐 Web application	6	WordPress · Next.js · Payload CMS · API (OWASP API Top 10) · Stripe webhooks · file upload safety
🏗️ Server & infrastructure	7	VPS · Cloudflare · Postgres · Docker · Kubernetes · DNS & domains · object storage (S3 / R2)
🛰 Distributed systems	3	Distributed-system audit · native-agent / client security · message bus (NATS / RabbitMQ / Kafka)
🎯 Architecture & reliability	2	Backend architecture (twelve-factor, stateless deploys) · backups & disaster recovery
🔎 Audit & review	2	Codebase audit methodology · site / server audit checklist
🔐 Identity & access	2	Auth hardening (NIST 800-63B, MFA tiers) · secret hygiene & rotation
📦 Supply chain & CI/CD	2	npm / pnpm / typosquat defense · GitHub Actions (OIDC, SHA pinning)
📋 Compliance (EU / DACH)	2	GDPR technical controls · DACH Impressum / Datenschutz / AGB
🔍 Detection & monitoring	2	Log strategy (operational / access / audit) · honeypots & tarpits
🛡️ Incident response	1	SANS PICERL runbook with post-mortem template
📨 Email security	1	SPF / DKIM / DMARC (with the p=none → p=reject migration path)
📱 Mobile security	2	iOS / macOS — Keychain, ATS, pinning · Android — Keystore, Play Integrity, WebView

Who this is for

• Developers shipping with LLM assistance ("vibe coders") who need a security checklist that actually fits how they work — agent loops, MCP servers, fast iterations, small teams
• Solo operators and small agencies running 5–50 WordPress sites, a few VPS servers, and Cloudflare — without a dedicated security team
• Engineers building LLM-powered features (chat, RAG, agents, MCPs) who need a defensive baseline against prompt injection, exfiltration, and runaway costs
• Anyone inheriting an undocumented production system who wants a fast, structured way to audit it

Each skill is defensive only. No exploitation, no offensive tradecraft. Authorization for the systems you work on is assumed.

Quick start

git clone https://github.com/GoldenWing-360/claude-security-skills.git

Use any skill in three ways:

1. As a Claude Code skill — Claude auto-triggers the right one based on the conversation. The YAML description field is matched against your request.
2. As a runbook for yourself — open <skill-name>/SKILL.md and follow the steps.
3. As a checklist for review — paste the skill into a PR or audit doc and walk through it.

Skill anatomy

Every SKILL.md follows a consistent structure that doubles as a discovery contract and a self-contained runbook:

---
name: <kebab-case-slug>
description: <three-sentence summary — what / covers / invoke when>
---

# <Skill title>

<one-paragraph framing>

## When to invoke
- <concrete situation>

## <Body — adaptive per skill>
detection · steps · patterns · common gotchas

## Quick checklist
- [ ] ...

## What this skill will not do
- <explicit non-goals — defensive-only stance>

A companion index.json at the repo root indexes every skill's slug, name, description, and domain for programmatic use (skill discovery, agent loading, search UIs).

Documentation

Reference material that complements the skills:

• 📝 Prompt Library — ready-to-use prompts that reliably trigger each of the 38 skills
• 📖 Security Glossary — definitions of terms used across the skills (BOLA, mTLS, RPO/RTO, slopsquatting, ...)
• ❓ FAQ — installation, compatibility, contribution flow, commercial use

Compatibility

Skills use plain Markdown with YAML frontmatter (name, description). Tested target is Claude Code; the same files work with any LLM coding agent that supports the convention — including Cursor, GitHub Copilot, Codex CLI, Cline, Continue.dev, and Gemini CLI. Nothing in the body is platform-specific.

Repository structure

<details> <summary>38 skills + repo metadata — click to expand</summary>

claude-security-skills/
├── .github/
│   ├── ISSUE_TEMPLATE/
│   │   ├── bug-report.md
│   │   ├── config.yml
│   │   └── skill-request.md
│   ├── workflows/
│   │   └── validate.yml
│   ├── dependabot.yml
│   ├── FUNDING.yml
│   ├── PULL_REQUEST_TEMPLATE.md
│   └── SOCIAL_PREVIEW.md
│
├── tools/
│   └── validate.py
│
├── agent-client-security/SKILL.md
├── ai-agent-guardrails/SKILL.md
├── android-security/SKILL.md
├── api-security/SKILL.md
├── auth-hardening/SKILL.md
├── backend-architecture/SKILL.md
├── backup-disaster-recovery/SKILL.md
├── cloudflare-hardening/SKILL.md
├── codebase-audit/SKILL.md
├── dach-compliance/SKILL.md
├── dependency-supply-chain/SKILL.md
├── distributed-system-audit/SKILL.md
├── dns-domain-security/SKILL.md
├── docker-container-security/SKILL.md
├── email-deliverability-security/SKILL.md
├── file-upload-security/SKILL.md
├── gdpr-technical-controls/SKILL.md
├── github-actions-security/SKILL.md
├── honeypot-tarpits/SKILL.md
├── incident-response/SKILL.md
├── ios-security/SKILL.md
├── kubernetes-security/SKILL.md
├── llm-app-security/SKILL.md
├── llm-coding-failure-modes/SKILL.md
├── log-strategy/SKILL.md
├── mcp-security/SKILL.md
├── message-bus-security/SKILL.md
├── nextjs-security/SKILL.md
├── object-storage-security/SKILL.md
├── payload-cms-security/SKILL.md
├── postgres-hardening/SKILL.md
├── prompt-injection-defense/SKILL.md
├── rag-security/SKILL.md
├── secret-hygiene/SKILL.md
├── site-server-audit/SKILL.md
├── stripe-webhook-security/SKILL.md
├── vps-hardening/SKILL.md
├── wordpress-hardening/SKILL.md
│
├── docs/
│   ├── README.md
│   ├── PROMPTS.md
│   ├── GLOSSARY.md
│   └── FAQ.md
│
├── CITATION.cff
├── CODE_OF_CONDUCT.md
├── CONTRIBUTING.md
├── index.json
├── LICENSE
├── README.md
└── SECURITY.md

Every skill is a self-contained SKILL.md with YAML frontmatter (name, description) plus a body that follows roughly: when to invoke → detection / steps / patterns → checklist → what this skill will not do.

</details>

Skills by category

Each link goes to the full SKILL.md with detection commands, step-by-step procedures, and checklists.

🤖 AI & LLM security

Skill	Summary
mcp-security	Audit MCP configurations, risk-tier capabilities, detect malicious servers, apply least-privilege scoping.
ai-agent-guardrails	Blast-radius classification, dry-run-first, out-of-band approval gates, kill switches.
prompt-injection-defense	Source-of-trust tagging, tool-use confirmation after untrusted input, exfiltration prevention.
llm-app-security	OWASP LLM Top 10 mapped to practical controls — rate limits, cost caps, PII scrubbing, audit logging.
llm-coding-failure-modes	Antipattern catalog for LLM coding agents — bulk ops, bypassed guards, slopsquatting, sycophancy.
rag-security	RAG pipelines — document-level authorization at retrieval time, tenant isolation in vector DBs, poisoned-corpus defense.

🌐 Web application

Skill	Summary
wordpress-hardening	Detect WordPress webshells and harden against re-compromise on shared hosting.
nextjs-security	Next.js-specific issues — middleware bypass, RSC over-fetch, NEXT_PUBLIC_ traps, CSP, next/image SSRF.
payload-cms-security	Access control, file uploads, GraphQL surface, and multi-tenant isolation in Payload CMS.
api-security	OWASP API Top 10 — BOLA, mass assignment, excessive data exposure, GraphQL depth limits.
file-upload-security	Accept uploads safely — magic-byte validation, polyglot defense, separate-origin serving with Content-Disposition.
stripe-webhook-security	Raw-body signature verification, idempotency, replay protection, currency-mismatch traps.
site-server-audit	Non-intrusive checklist for DNS, TLS, security headers, exposed paths, and cookies.

🏗️ Server & infrastructure

Skill	Summary
vps-hardening	30-minute Debian / Ubuntu baseline — SSH key-only, UFW, fail2ban, unattended-upgrades.
cloudflare-hardening	Origin-IP protection, WAF, Rate Limiting, Zero Trust Access, Transform Rules for headers.
postgres-hardening	pg_hba, role separation, row-level security, TLS, encrypted backups, pg_audit.
docker-container-security	Non-root users, read-only filesystems, dropped capabilities, image scanning, the UFW-bypass trap.
kubernetes-security	Pod Security Standards, RBAC least-privilege, NetworkPolicy default-deny, admission controllers.
dns-domain-security	Dangling records and subdomain takeover, registrar lock, CAA, DNSSEC tradeoffs, CT-log monitoring.
object-storage-security	S3 / R2 / GCS — public-access audit, presigned URLs done right, scoped credentials, object lock.

🛰 Distributed systems

Skill	Summary
distributed-system-audit	Map first, judge later — trust boundaries, protocol audit (replay / ordering / forgery), failure-mode walk.
agent-client-security	Native agents on customer machines — installer signing, OTA with rollback, mTLS, anti-tampering signals.
message-bus-security	NATS / RabbitMQ / Kafka — tenant isolation, deny-default permissions, replay protection, consumer idempotency.

🎯 Architecture & reliability

Skill	Summary
backend-architecture	Stateless apps, state in the right places, twelve-factor — survive redeploys, scaling, server reboots.
backup-disaster-recovery	RPO / RTO, 3-2-1, encrypted off-host backups, ransomware-resistant immutable storage, restore drills.

🔎 Audit & review

Skill	Summary
codebase-audit	Methodology for inherited codebases — triage, SAST / SCA recipes, OWASP grep patterns, severity-classed report.

🔐 Identity & access

Skill	Summary
auth-hardening	NIST 800-63B passphrases, Argon2id, MFA tiers, no-enumeration lockout, password reset done right.
secret-hygiene	Find leaked secrets, rotate in the right order, optionally purge git history with git-filter-repo.

📦 Supply chain & CI/CD

Skill	Summary
dependency-supply-chain	Lockfile hygiene, behavior-level scanning, postinstall review, typosquat and slopsquat defense.
github-actions-security	SHA-pinned actions, scoped GITHUB_TOKEN, OIDC in place of long-lived cloud secrets.

📋 Compliance (EU / DACH)

Skill	Summary
gdpr-technical-controls	Data inventory, SAR and deletion endpoints, log scrubbing, 72-hour breach notification.
dach-compliance	Impressum, Datenschutzerklärung, AGB, AVV / DPA, TOMs, cookie consent for Germany / Austria / Switzerland.

🔍 Detection & monitoring

Skill	Summary
log-strategy	What to log and what never to log — operational vs access vs audit, retention tiers, alert routing.
honeypot-tarpits	Fake admin paths, canary tokens, decoy .env files — high-signal detection without a SIEM.

🛡️ Incident response

Skill	Summary
incident-response	SANS PICERL runbook for small teams, with a post-mortem template.

📨 Email security

Skill	Summary
email-deliverability-security	SPF / DKIM / DMARC with the p=none → p=quarantine → p=reject migration path.

📱 Mobile security

Skill	Summary
ios-security	Keychain accessibility tiers, ATS, certificate pinning, file protection, jailbreak detection as signal.
android-security	Keystore + StrongBox, exported components, WebView hardening, backup rules, Play Integrity as signal.

Find the right skill

Scenario	Where to start
Site hacked / webshell found	incident-response → wordpress-hardening
Detect a webshell on WordPress	wordpress-hardening
Committed a .env to a public repo	secret-hygiene
Preventing prompt injection in an LLM app	prompt-injection-defense
Reviewing LLM-generated code	llm-coding-failure-modes
Giving an AI agent write access to production	ai-agent-guardrails
Hardening a new Ubuntu VPS	vps-hardening
Hardening a Kubernetes cluster	kubernetes-security
User uploads disappear on redeploy	backend-architecture
Architecting a backend that scales	backend-architecture
Zero-downtime deploys	backend-architecture
Inherited a codebase, where to start	codebase-audit
Auditing a distributed / agent system	distributed-system-audit
Fleet of native agents on customer machines	agent-client-security
Multi-tenant NATS / RabbitMQ / Kafka	message-bus-security
Backups exist but have never been restored	backup-disaster-recovery
Broken access control / BOLA in an API	api-security
Accepting user file uploads safely	file-upload-security
Cloudflare WAF / origin-IP protection	cloudflare-hardening
Securing a Stripe webhook	stripe-webhook-security
Implementing OWASP LLM Top 10	llm-app-security
GitHub Actions OIDC + scoped tokens	github-actions-security
DACH Impressum / Datenschutz / AGB	dach-compliance
Blocking brute force on /wp-login.php	wordpress-hardening + vps-hardening + cloudflare-hardening
Writing a post-mortem after a breach	incident-response
Configuring SPF / DKIM / DMARC	email-deliverability-security
CNAME points at a deprovisioned service (subdomain takeover)	dns-domain-security
S3 / R2 bucket accidentally public	object-storage-security
RAG answers leak documents users shouldn't see	rag-security
Shipping an Android app that holds tokens	android-security

Using with Claude Code

Drop the directory in a path Claude Code scans for skills, or reference the skills directly. Claude matches the YAML description against your request and loads the matching SKILL.md. If you prefer to work without auto-triggering, just cat the relevant SKILL.md and follow it manually.

Contributing

Contributions welcome, especially:

• Additional detection patterns observed in the wild (with IOCs anonymized)
• Updated rotation procedures as providers change their APIs
• Translations (the original is English; the maintainer also operates in German)
• New skills for under-covered areas

Please keep contributions defensive in spirit. No exploitation tradecraft, no recommendations to weaken existing protections.

License

MIT.

Maintainers

Maintained by GoldenWing. Patterns here are distilled from real cleanup, hardening, and incident-response work. Specific indicators of compromise and customer details have been generalized so the guidance is portable.