pith. sign in

arxiv: 2602.13379 · v2 · pith:NWMCIAQQnew · submitted 2026-02-13 · 💻 cs.CR · cs.AI· cs.CL· cs.LG· cs.SE

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

classification 💻 cs.CR cs.AIcs.CLcs.LGcs.SE
keywords multi-turnsafetyagentsagenttoolshieldattackaveragebenchmark
0
0 comments X
read the original 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 (Multi-Turn Agent Risk Benchmark), the first benchmark to evaluate multi-turn tool-using agent safety. 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 https://github.com/CHATS-lab/ToolShield.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

    cs.CL 2026-05 unverdicted novelty 7.0

    Boiling the Frog is a new stateful multi-turn benchmark for agentic safety that reports an aggregate strict attack success rate of 44.4% across nine models, with rates ranging from 20.5% to 92.9% depending on the mode...

  2. Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

    cs.CL 2026-05 unverdicted novelty 7.0

    Boiling the Frog is a new stateful multi-turn benchmark that finds an aggregate 44.4% strict attack success rate for incremental safety violations across nine AI models, with rates ranging from 20.5% to 92.9%.

  3. Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback

    cs.CR 2026-05 unverdicted novelty 7.0

    Presents TRUST-Bench benchmark for hidden-trigger tool compromises in LLM agents and VISTA-Guard framework for trajectory-aware risk scoring of final actions under untrusted feedback.

  4. Security Considerations for Multi-agent Systems

    cs.CR 2026-03 unverdicted novelty 6.0

    No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.