Skip to content

LLM-Coding/vibe-coding-risk-radar

Repository files navigation

Vibe-Coding Risk Radar

MECE risk framework for AI-generated code — 5 dimensions, 4 tiers, actionable mitigations.

What is this?

An interactive React component that classifies vibe-coding risk across 5 orthogonal dimensions and maps results to concrete mitigation tiers. Accompanied by full AsciiDoc documentation with 30+ verified references.

Features

  • 5 MECE Dimensions: Code type, language safety, deployment context, data sensitivity, blast radius

  • 4 Cumulative Tiers: Each tier includes all mitigations of lower tiers

  • Radar Chart: SVG visualization of the risk profile

  • Presets: Quick scenarios (Landing Page → Payment Service)

  • DE / EN: Full bilingual support, switchable at runtime

  • Inline Documentation: Slide-out sidebar with all 6 doc sections

  • Mobile-friendly: Responsive layout with stacked sliders

Quick Start

Local Development

npm install
npm run dev

Production Build

npm run build
npm run preview

Output in dist/.

GitHub Pages Deployment

The included GitHub Action (.github/workflows/deploy.yml) handles everything automatically:

  1. Builds the React app with Vite

  2. Renders the AsciiDoc documentation with Asciidoctor

  3. Deploys both to GitHub Pages

Setup

  1. Go to Settings → Pages in your GitHub repository

  2. Under Build and deployment, select GitHub Actions as the source

  3. Push to main — the workflow runs automatically

After deployment:

Project Structure

.
├── .github/workflows/deploy.yml   # GitHub Pages CI/CD
├── docs/
│   └── risk-radar.adoc            # Full AsciiDoc documentation (30+ refs)
├── src/
│   ├── RiskRadar.jsx              # Main React component (self-contained)
│   ├── main.jsx                   # React entry point
│   └── index.css                  # Minimal reset
├── index.html                     # Vite entry HTML
├── package.json
├── vite.config.js
└── README.adoc

Documentation

The docs/risk-radar.adoc file contains the full framework documentation:

  • Empirical evidence (Veracode, CodeRabbit, METR, Perry et al.)

  • 5×5 dimension matrix with detailed descriptions

  • 4-tier mitigation model with deterministic, probabilistic, and organizational measures

  • Regulatory context (EU AI Act, HIPAA, PCI-DSS, IEC 61508, DO-178C, ISO 26262)

  • References: 30+ verified URLs to primary sources

License

MIT

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •