Skip to main content
skill CX Codex

cloudflare-security-audit-skill — Claude Code skill: security audit

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.

no license 216 installs ★ 13 updated 2026-10-09

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a claude-code
Open on GitHub

What cloudflare-security-audit-skill 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.

What it helps with

  • 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 for the agent

  • 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

How to install cloudflare-security-audit-skill

1Skills CLI (Vercel)

npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a claude-code

2Manually: put the files in place

~/.claude/skills/cloudflare-security-audit-skill/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cloudflare-security-audit-skill/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about cloudflare-security-audit-skill

How do I install cloudflare-security-audit-skill in Claude Code?

Run npx skills add reason-machines/security-skills --skill cloudflare-security-audit-skill -a claude-code. The skill file ends up at ~/.claude/skills/cloudflare-security-audit-skill/SKILL.md.

What does cloudflare-security-audit-skill do?

It runs a security audit in six stages: mapping, a parallel hunt by seven agents, adversarial review of each finding, reporting, findings.json output and an independent check against the source.

What happens if I run it twice on the same repo?

The passes add up. A new run reads the findings.json from earlier ones and moves into code that has not been covered yet; the run number shows up in the run-<N> directory and in the output metadata.

Similar skills

All skills for Security →
mcp-security-audit official github mcp-security-audit scans .mcp.json files for hardcoded secrets, shell injection patterns, and unpinned package dependencies. Runs before commits or when onboarding new MCP servers to a repository. CX Codex +1 1,100installs security-audit cloudflare security-audit reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks. CX Codex +1 116,100installs js-security-audit c0x12c js-security-audit runs a 5-area security check on JS and TS projects across repository settings, supply-chain hygiene, CI/CD, and alerts. Flags critical risks before release. CX Codex +1 ★ 111repo stars deep-security-scan official openai deep-security-scan is a Claude Code skill that runs deep, multi-pass repository security audits, combining findings until consecutive scans reveal nothing new. CX Codex +1 127installs claude-security official Anthropic claude-security is a Claude Code skill that scans repositories for vulnerabilities, inspects pull request diffs, and writes verified patch files. CX Codex +1 2,304installs git-guardrails-claude-code Matt Pocock The git-guardrails-claude-code skill adds a Claude Code hook that stops risky Git commands before they run. Use it when an agent must not push or discard working-tree changes. CX Codex +1 499,069installs ponytail-review DietrichGebert ponytail-review is a Claude Code skill that reviews code changes for bugs, risks, and unnecessary complexity. It responds to requests to inspect a commit, PR, branch, or files. CX Codex +1 75,500installs reverse-engineer-anything morluto The reverse-engineer-anything skill for Claude Code and other platforms analyzes compiled binaries, packages, and proprietary code. It extracts data from executables or archives for decompilation and version comparison. CX Codex +1 18,800installs

From the same set129

The whole set →
androidstudio-app-pentest-environment The androidstudio-app-pentest-environment skill guides setup of an Android Studio emulator for app security testing, covering Magisk root access, Frida instrumentation, and HTTPS traffic inspection. CX Codex +1 233installs android-pentest-environment-setup android-pentest-environment-setup walks you through a rooted Android Studio emulator with Magisk, Frida and proxy traffic capture for app pentesting. CX Codex +1 226installs spoof-suite-hardware-identity spoof-suite-hardware-identity — a Claude Code skill that configures hardware identifier and network fingerprint masking for authorized security testing and privacy research. Runs across multiple AI coding platforms. CX Codex +1 219installs hardware-hardspoof-spoofing-toolkit hardware-hardspoof-spoofing-toolkit — a skill that walks the agent through hardsp00f: MAC swaps, SMBIOS strings, DNS and SNI behaviour, browser fingerprint traits. Built for permitted testing on a box you control. CX Codex +1 218installs bitdefender-total-security-workflow bitdefender-total-security-workflow standardizes Bitdefender Total Security maintenance on Windows, covering scan routines, quarantine reviews, and exclusion tracking. CX Codex +1 215installs pentesting-checklist-guide pentesting-checklist-guide guides security testing across 23 target platforms, explaining how to manage 1,000+ checks, record findings, and export audit reports. CX Codex +1 184installs pentesting-checklist-security-assessment pentesting-checklist-security-assessment — a checklist skill for security work: 23 platforms and 1,000+ checks, from web apps and APIs to Kubernetes and LLM. CX Codex +1 180installs pentesting-checklist-platform pentesting-checklist-platform gives the agent a structured checklist with over a thousand security checks across 23 platforms, from web and API to Kubernetes and LLM. CX Codex +1 177installs

Project sponsors

Companies that keep this analytics open