Security research - agents - guardrails
Security systems, built in public.
A focused index of security work across agent containment, secret detection, threat modeling, authorization, accessibility auditing and OWASP research.
Security index
13Projects
6Domains
4OWASP guides
Selected workSecurity highlights
Selected builds that make security work practical: find leaks, model threats, contain agent execution and review real code paths.
Complete indexSecurity project catalog
Source links for security projects and research in the AI Playground repository. Browse all AI work ↗
Showing projectsSource: security catalog