A multi-agent application-security review harness for Claude Code (and, later, other AI agents). One router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts vulnerabilities with a per-class knowledge base, chains findings into escalations, verifies real impact, and reports to README/JSON/SARIF/doc/PDF.

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.