vibe-security
Audits codebases for common security vulnerabilities that AI coding assistants introduce in "vibe-coded" applications. Checks for exposed API keys, broken access control (Supabase RLS, Firebase rules), missing auth validation, client-side trust issues, insecure payment flows, and more. Use this skill whenever the user asks about security, wants a code review, mentions "vibe coding", or when you're writing or reviewing code that handles authentication, payments, database access, API keys, secrets
Security Assessment
Detected risks:
About vibe-security
The vibe-security skill audits codebases for common security vulnerabilities that AI coding assistants frequently introduce when building applications rapidly. It specifically targets issues prevalent in "vibe-coded" projects — applications developed quickly with AI assistance where security fundamentals are often overlooked or skipped. This skill exists because AI assistants consistently produce insecure patterns that lead to real-world breaches, exposed API keys, and compromised billing accounts.
The skill performs systematic security audits across nine critical areas: secrets and environment variables, database access control (Supabase RLS, Firebase rules), authentication and authorization, rate limiting, payment security, mobile security, AI/LLM integration security, deployment configuration, and data access patterns. It operates on the core principle that clients can never be trusted — all prices, user IDs, roles, subscription statuses, and access controls must be validated server-side. The skill uses modular reference files to examine only relevant technologies actually present in the codebase, making audits efficient and focused.
This skill is designed for developers building web and mobile applications with modern frameworks, particularly those using AI assistance for rapid development. It's especially valuable when working with authentication systems, payment integrations, database access layers, or any code handling user data and secrets. The skill can be invoked proactively during code generation to prevent vulnerabilities from being introduced, or reactively when users request security reviews, code audits, or ask questions like "is this safe?" or "can someone hack this?"
FAQ
When should I use the vibe-security skill?
Use this skill whenever you're working with authentication, payments, database access, API keys, secrets, or user data. It's also triggered automatically when you ask for security reviews, code audits, or mention terms like "vibe coding", "is this safe?", or "check my code".
What technologies and frameworks does this skill support?
The skill supports Supabase RLS, Firebase Security Rules, Convex auth guards, JWT authentication, Next.js, React Native, Expo, and general web/mobile patterns. It only examines technologies actually present in your codebase, skipping irrelevant sections automatically.
Does this skill perform a full security audit or focus on specific vulnerabilities?
It focuses specifically on vulnerabilities commonly introduced by AI code generation — exposed secrets, broken access control, missing auth validation, client-side trust issues, insecure payment flows, and similar patterns. It does not nitpick style or non-security concerns.
Can this skill prevent vulnerabilities when writing new code?
Yes. The skill can be used proactively while generating code to consult security best practices and avoid introducing vulnerabilities in the first place, not just for auditing existing code.
What gets prioritized in security reports?
Issues are prioritized by exploitability and real-world impact. Critical issues like exposed secrets, disabled RLS, or authentication bypasses are flagged immediately at the top of responses.
All Files
11 filesInstall vibe-security
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
raroque/vibe-security-skill