arXiv cs.CL
· Papers
Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
arXiv:2606.26479v1 Announce Type: cross Abstract: Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training the model to refuse malicious instructions, enforce security outside the model with a deterministic policy that mediates th