D. Molinos

Who Guards the Guard? Evaluating Deterministic, LLM-Based, and Hybrid Firewalls for Tool-Using Agents

Tool-using large language model (LLM) agents process untrusted files, URLs, and tables at a boundary where data may be mistaken for instructions. This paper compares four interface-level conditions: no firewall, deterministic policy enforcement, an LLM-based Tool-Input Minimizer/Tool-Output Sanitizer, and a gated hybri...