FlagThis

Abstract

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents _can_ do and _should_ do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing new risks overlooked by existing benchmarks. To systematically scale safety testing into multi-turn, tool-realistic settings, we propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences. Using this taxonomy, we construct **MT-AgentRisk** ( **M** ulti- **T** urn **Agent Risk** Benchmark), the first benchmark to evaluate tool-using agent safety under multi-turn, harmful-distribution settings. Our experiments reveal substantial safety degradation: the Attack Success Rate (ASR) increases by 16% on average across open and closed models in multi-turn settings. To close this gap, we propose **ToolShield** , a training-free, tool-agnostic, self-exploration defense: when encountering a new tool, the agent autonomously generates test cases, executes them to observe downstream effects, and distills safety experiences for deployment. Experiments show that ToolShield effectively reduces ASR by 30% on average in multi-turn interactions. Our code is available at CHATS-lab/ToolShield.