# cloudflare-security-audit-skill

cloudflare-security-audit-skill runs a six-stage security audit over a repo with parallel agents, then hands back a report and schema-checked findings.json.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 216 installs · ★ 13 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/cloudflare-security-audit-skill/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit-skill

## What it does

The skill works through six stages: mapping the codebase, hunting, adversarial review, a written report, machine-readable output, and a final independent check. Hunting fans out to seven agents at once, each with its own angle: injection, access control, business logic, crypto, feature abuse, chained attacks and an open-ended pass. The mapping stage writes `architecture.md` with the entry points and data flows it found.

Every finding goes back to an agent that did not produce it, and that reviewer argues against it. Anything without a reproducible path gets dropped before reporting. A finished run leaves `REPORT.md`, `FINDINGS-DETAIL.md` for MEDIUM and above, `findings.json` matched against `report-schema.json`, and the review transcripts under `validation-logs/`.

Expect a short list rather than a long one. Only issues with a payload and a visible effect are accepted; a missing second layer of defence behind one that holds is filed as hardening, not as a vulnerability. Repeat passes over the same repo build on each other, because each new run reads earlier `findings.json` files and heads for untouched areas. Results land in `~/security-audit-skill/<repo-name>/run-<N>` unless you name a directory.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/cloudflare-security-audit-skill/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/cloudflare-security-audit-skill/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/cloudflare-security-audit-skill/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/cloudflare-security-audit-skill/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills skills/cloudflare-security-audit-skill
```

2. **Manually: put the files in place**
- File: `.github/skills/cloudflare-security-audit-skill/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/security-skills --path skills/cloudflare-security-audit-skill
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/cloudflare-security-audit-skill/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/security-skills/tree/HEAD/skills/cloudflare-security-audit-skill/SKILL.md

## When to use it
- Run a pre-release security pass and get confirmed findings
- Drop false positives before they reach the report
- Produce `findings.json` for automated triage
- Audit just the auth or payment module instead of the whole codebase
- Split coverage across several passes over one repo

## Example prompts
- Audit this codebase for security issues and save the results to `~/audits/myapp`
- Find vulnerabilities in `./src/auth` and give me both the report and `findings.json`
- Run a second audit pass on this repo and skip what the earlier runs already found

## Similar
- [mcp-security-audit](https://affpapa.org/en/nevibecode/skills/mcp-security-audit.md) — skill · 1100 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 116100 installs
- [js-security-audit](https://affpapa.org/en/nevibecode/skills/js-security-audit.md) — skill · ★ 111 repo stars
- [deep-security-scan](https://affpapa.org/en/nevibecode/skills/openai-deep-security-scan.md) — skill · 127 installs
- [claude-security](https://affpapa.org/en/nevibecode/skills/claude-security.md) — skill · 2304 installs
- [git-guardrails-claude-code](https://affpapa.org/en/nevibecode/skills/git-guardrails-claude-code.md) — skill · 499069 installs
- [ponytail-review](https://affpapa.org/en/nevibecode/skills/ponytail-review.md) — skill · 75500 installs
- [reverse-engineer-anything](https://affpapa.org/en/nevibecode/skills/reverse-engineer-anything.md) — skill · 18800 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 129 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
