Skip to content
Back to search

vibe-security-skill

SkillWorks with Claude CodeGitHub

Agent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/raroque-vibe-security-skill/badge.svg)](/listings/raroque-vibe-security-skill)

HTML

<a href="/listings/raroque-vibe-security-skill"><img src="/api/listings/raroque-vibe-security-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Code

npx skills add https://github.com/raroque/vibe-security-skill --skill vibe-security

If `npx` isn't available, install Node.js first: `brew install node` (macOS) or download from [nodejs.org](https://nodejs.org).

OpenAI Codex

npx skills add https://github.com/raroque/vibe-security-skill --skill vibe-security

Select "Codex" when prompted for the agent platform.

Manual Installation (Claude Code)

Clone this repo and copy the `vibe-security/` folder to your project or global skills directory:

# Project-level (applies to one project)
cp -r vibe-security/ .claude/skills/vibe-security/

# Global (applies to all projects)
cp -r vibe-security/ ~/.claude/skills/vibe-security/

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 87 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="https://img.shields.io/badge/security-vibe--coded%20apps-DC2626.svg" alt="Security for vibe-coded apps" />
  3. <img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT License" />
  4. <a href="https://twitter.com/raroque">
  5. <img src="https://img.shields.io/badge/Contact-@raroque-95a5a6.svg?style=flat" alt="Twitter: @raroque" />
  6. </a>
  7. </p>
  8. <h1 align="center">Vibe Security - Agent Skill for AI Coding Assistants</h1>
  9. An agent skill that helps secure vibe-coded apps - or honestly any app - from common security vulnerability patterns. Built by [Chris Raroque](https://www.youtube.com/@raroque) ([@raroque](https://twitter.com/raroque)) in collaboration with my colleagues at [Aloa](https://aloa.co).
  10. AI assistants are great at building features fast but consistently get security wrong: hardcoding secrets, skipping row-level security, trusting client-submitted prices, storing tokens in localStorage. This skill catches those patterns before they ship.
  11. **Need help building AI apps, custom agents, or implementing AI at your company?** Work with Chris and the team at [Aloa](https://aloa.co).
  12. ## Background
  13. This skill was built specifically to address the security issues that keep showing up in vibe-coded applications. When you're building fast with AI, security fundamentals get skipped - and the AI assistants themselves are often the ones introducing the vulnerabilities. This skill gives your agent the knowledge to catch and prevent those patterns.
  14. It uses the [Agent Skills](https://agentskills.io/home) format, so it works with Claude Code, OpenAI Codex, and other compatible agents.
  15. The security rules are organized as reference files that the agent loads based on what technologies your project uses. If you're using Supabase, it checks RLS policies. If you're using Stripe, it checks payment flows. If you're using React Native, it checks for secrets in the JS bundle. No wasted context on irrelevant checks.
  16. ## Installing Vibe Security
  17. ### Claude Code
  18. ```bash
  19. npx skills add https://github.com/raroque/vibe-security-skill --skill vibe-security
  20. ```
  21. If `npx` isn't available, install Node.js first: `brew install node` (macOS) or download from [nodejs.org](https://nodejs.org).
  22. ### OpenAI Codex
  23. ```bash
  24. npx skills add https://github.com/raroque/vibe-security-skill --skill vibe-security
  25. ```
  26. Select "Codex" when prompted for the agent platform.
  27. ### Manual Installation (Claude Code)
  28. Clone this repo and copy the `vibe-security/` folder to your project or global skills directory:
  29. ```bash
  30. # Project-level (applies to one project)
  31. cp -r vibe-security/ .claude/skills/vibe-security/
  32. # Global (applies to all projects)
  33. cp -r vibe-security/ ~/.claude/skills/vibe-security/
  34. ```
  35. ## Using Vibe Security
  36. **Claude Code:** Use `/vibe-security` to trigger a full security audit, or just ask naturally - "check my code for security issues", "is this safe?", "audit this project".
  37. **Codex:** Use `$vibe-security` or describe what you need - "review this for vulnerabilities", "check my Supabase RLS".
  38. The skill also activates automatically when you're writing or reviewing code that handles authentication, payments, database access, API keys, or user data.
  39. ## What It Checks
  40. | Category | What It Catches |
  41. |----------|----------------|
  42. | **Secrets & Env Vars** | Hardcoded API keys, secrets in `NEXT_PUBLIC_`/`VITE_`/`EXPO_PUBLIC_` vars, missing `.gitignore` |
  43. | **Database Security** | Disabled Supabase RLS, `USING (true)` policies, missing `WITH CHECK`, exposed sensitive fields, Firebase `allow: if true` rules, Convex missing auth |
  44. | **Auth & Authorization** | `jwt.decode()` without verify, middleware-only auth, unprotected Server Actions, tokens in localStorage |
  45. | **Rate Limiting** | Missing limits on auth/AI/email endpoints, client-tamperable rate counters, no billing caps |
  46. | **Payments** | Client-submitted prices, missing webhook signature verification, stale subscription checks |
  47. | **Mobile** | API keys in JS bundle, `AsyncStorage` for tokens, unsafe deep links, weak biometric auth |
  48. | **AI / LLM** | Exposed AI API keys, no usage caps, prompt injection, unsafe output rendering |
  49. | **Deployment** | Debug mode in production, exposed source maps, missing security headers, `.git` accessible |
  50. | **Data Access** | SQL injection, Prisma operator injection, `$queryRawUnsafe`, mass assignment |
  51. ## Contributing
  52. Contributions, corrections, and improvements are very welcome! This is meant to be a community resource. If you've found a security anti-pattern that AI assistants keep introducing, please add it.
  53. See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
  54. ## License
  55. Vibe Security is available under the MIT License. See [LICENSE](LICENSE) for details.
  56. Created by [Chris Raroque](https://www.youtube.com/@raroque) ([@raroque](https://twitter.com/raroque)) and the team at [Aloa](https://aloa.co).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.