Craig Brown

Open-source security audit framework covering all 10 OWASP Agentic AI threat categories (ASI01-ASI10). Scan multi-agent systems for prompt injection, data exfiltration, broken access control, and 7 more categories. Returns risk scores (0-100) with remediation priorities. Free tie

Privacy-preserving agent settlement for prediction markets via blind signatures. 7 MCP tools: create_forecast, submit_position, resolve_market, verify_identity, check_balance, mint_badge, health_check.