Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

Audit and fix your Mac's security in one command. No agent, no signup, open source.

Structured project lifecycle plugin for Claude Code — from idea to production with discipline, parallel agents, and quality gates.

Audit AI applications and agents for security risks before commit, PR, merge, or deployment. Deterministic findings with coverage and evidence receipts.

Blitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.