Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents

Paper recorded by Signals 4 on 2026-10-02 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-02 on arXiv · recorded by Signals 4 on 2026-10-05

Category: cs.CL · 自然语言处理 · first seen 2026-10-05

Abstract

LLM agents increasingly screen tool outputs with small prompt-injection detectors, and teams choose among detectors by their scores on public benchmarks. We ask whether those scores predict how a detector behaves inside an agent. We replay the ground-truth tool calls of two agent benchmarks, AgentDojo and tau-bench, without an LLM to obtain tool outputs that are benign by construction, label injec

Read on arXiv →