Papers
arxiv:2509.07315

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs

Published on Sep 9, 2025
Authors:
,
,
,
,
,

Abstract

A new benchmark and framework are proposed to prospectively assess and improve the safety of large language model tool use against malicious instructions and risky toolsets.

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify potential risks such as financial loss or privacy leakage with ambiguous or malicious user instructions. Compared to previous studies, which mainly assess the safety awareness of LLMs after obtaining the tool execution results (i.e., retrospective evaluation), this paper focuses on prospective ways to assess the safety of LLM tool utilization, aiming to avoid irreversible harm caused by directly executing tools. To this end, we propose SafeToolBench, the first benchmark to comprehensively assess tool utilization security in a prospective manner, covering malicious user instructions and diverse practical toolsets. Additionally, we propose a novel framework, SafeInstructTool, which aims to enhance LLMs' awareness of tool utilization security from three perspectives (i.e., User Instruction, Tool Itself, and Joint Instruction-Tool), leading to nine detailed dimensions in total. We experiment with four LLMs using different methods, revealing that existing approaches fail to capture all risks in tool utilization. In contrast, our framework significantly enhances LLMs' self-awareness, enabling a more safe and trustworthy tool utilization.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2509.07315
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.07315 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.07315 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.