arXiv:2511. 20597v2 Announce Type: replace-cross Abstract: The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models.
By Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley, Jerry Ma, Denis Yarats, Ninghui Li
arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.
By Zihao Wang, Yiming Li, Yutong Wu, Zheyu Liu, Kangjie Chen, Fok Kar Wai, Pin-Yu Chen, Vrizlynn L. L. Thing, Bo Li, Dacheng Tao, Tianwei Zhang
arXiv:2606. 12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources.
By Pengfei He, Lesly Miculicich, Vishesh Sharma, Ash Fox, George Lee, Jiliang Tang, Tomas Pfister, Long T. Le
arXiv:2607. 08147v1 Announce Type: cross Abstract: Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces.
By Corban Villa, Alp Eren Ozdarendeli, Sijun Tan, Raluca Ada Popa
arXiv:2606. 04425v1 Announce Type: cross Abstract: Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions through memories, filesystems, tools, and other long-lived contextual artifacts.
By Yuanbo Xie, Tianyun Liu, Yingjie Zhang, Suchen Liu, Yulin Li, Liya Su, Tingwen Liu
WAInjectBench introduces the first comprehensive benchmark for detecting prompt injection attacks against web agents, offering a fine‑grained categorization of threats and datasets that include malicious and benign text and image samples. The study systematically evaluates both text‑based and image‑based detection methods across multiple scenarios, revealing that detectors perform well on attacks with explicit instructions or visible perturbations but struggle with subtle or instruction‑free attacks. The authors release the datasets and code to facilitate further research in this area.
By Yinuo Liu, Xilong Wang, Ruohan Xu, Yuqi Jia, Neil Zhenqiang Gong