H-18Guardrail Middleware
A policy layer wraps the loop and evaluates every proposed action before anything executes.
Further reading
- Defeating Prompt Injections by Design Debenedetti et al., 2025
- Design patterns for securing LLM agents against prompt injections Simon Willison, 2025
- OWASP Top 10 for Large Language Model Applications OWASP GenAI Security Project