S-12Dual-LLM / Quarantined Reader
The model that holds the tools never reads untrusted text; a quarantined model with no tools reads it and returns only a symbolic handle.
Further reading
- The Dual LLM pattern for building AI assistants that can resist prompt injection Simon Willison, 2023
- Defeating Prompt Injections by Design Debenedetti et al., 2025
- Design patterns for securing LLM agents against prompt injections Simon Willison, 2025