60-rule static security scanner and MCP skill poisoning auditor that detects leaked secrets, unguarded API routes, missing database RLS, and prompt injection in AI-generated codebases.
Enables coding agents to audit frontend source for generic AI UI patterns and WCAG 2.1 contrast failures, extract Design DNA from local stylesheets or live URLs, and export Tailwind v4 tokens. It also applies complete design presets to synchronize agent rule files and MCP configuration.