Guardado en:
Detalles Bibliográficos
Autores principales: Kong, Dezhang, Wu, Zhuxi, Liu, Shiqi, Tan, Zhicheng, Lu, Kuichen, Li, Minghao, Liu, Qichen, Chu, Shengyu, Xu, Zhenhua, Liu, Xuan, Han, Meng
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.18113
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910051326754816
author Kong, Dezhang
Wu, Zhuxi
Liu, Shiqi
Tan, Zhicheng
Lu, Kuichen
Li, Minghao
Liu, Qichen
Chu, Shengyu
Xu, Zhenhua
Liu, Xuan
Han, Meng
author_facet Kong, Dezhang
Wu, Zhuxi
Liu, Shiqi
Tan, Zhicheng
Lu, Kuichen
Li, Minghao
Liu, Qichen
Chu, Shengyu
Xu, Zhenhua
Liu, Xuan
Han, Meng
contents LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accepting a disguised malicious URL enables subsequent access to unsafe webpages, which can cause severe damage to service providers and users. Despite this risk, no benchmark currently targets this emerging threat. To address this gap, we propose MalURLBench, the first benchmark for evaluating LLMs' vulnerabilities to malicious URLs. MalURLBench contains 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites. Experiments with 12 popular LLMs reveal that existing models struggle to detect elaborately disguised malicious URLs. We further identify and analyze key factors that impact attack success rates and propose URLGuard, a lightweight defense module. We believe this work will provide a foundational resource for advancing the security of web agents. Our code is available at https://github.com/JiangYingEr/MalURLBench.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18113
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
Kong, Dezhang
Wu, Zhuxi
Liu, Shiqi
Tan, Zhicheng
Lu, Kuichen
Li, Minghao
Liu, Qichen
Chu, Shengyu
Xu, Zhenhua
Liu, Xuan
Han, Meng
Cryptography and Security
Artificial Intelligence
LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accepting a disguised malicious URL enables subsequent access to unsafe webpages, which can cause severe damage to service providers and users. Despite this risk, no benchmark currently targets this emerging threat. To address this gap, we propose MalURLBench, the first benchmark for evaluating LLMs' vulnerabilities to malicious URLs. MalURLBench contains 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites. Experiments with 12 popular LLMs reveal that existing models struggle to detect elaborately disguised malicious URLs. We further identify and analyze key factors that impact attack success rates and propose URLGuard, a lightweight defense module. We believe this work will provide a foundational resource for advancing the security of web agents. Our code is available at https://github.com/JiangYingEr/MalURLBench.
title MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2601.18113