MCP server exposing Bawbel Scanner as agent-callable tools. Scan MCP servers, skill files, and system prompts for AVE vulnerabilities mid-conversation.

LYAR is a forensic engine for deception detection built with Python (OOP/RegEx). It identifies linguistic distancing, narrative gaps & cognitive load. Features: automated weighted risk scoring, batch processing, visual data charts (Matplotlib), and professional HTML reports. Designed for security & investigative support.

Django authentication backend implementing Amnesia Honeywords for breach detection without a separate honeychecker. Stores k hashed candidates per user, flags logins using unmarked decoys, logs events, and emits signals for alerting. Integrates via settings + migrations; initialize users at signup/password change.