The paper introduces CTF-ABACUS, a trace-based auditing framework that reconstructs each autonomous language-model agent’s run in Capture-the-Flag (CTF) challenges into evidence‑grounded solve profiles. By decomposing actions into penetration‑testing phases and techniques, it distinguishes genuine exploitation from shortcut methods such as memorized recall or guessing. Applying the framework to 1,435 CTF attempts by six models on 240 challenges shows that only 62‑87% of recovered flags are trace‑verified, highlighting that many successes rely on shallow trajectories rather than true exploitation.
By Kimberly Milner, Minghao Shao, Nanda Rani, Haoran Xi, Venkata Sai Charan Putrevu, Meet Udeshi, Sandeep K. Shukla, Prashanth Krishnamurthy, Farshad Khorrami, Muhammad Shafique, Ramesh Karri
arXiv:2608.30207v1 Announce Type: cross
Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...
By Chen Xiong, Zhiyuan He, Pin-Yu Chen, Stjepan Picek, Tsung-Yi Ho
arXiv:2607. 18659v1 Announce Type: cross Abstract: LLM-based browser agents are rapidly changing the threat landscape for web security.
By Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud, Dillan Bailey, Amin Kharraz
arXiv:2607. 26314v1 Announce Type: cross Abstract: Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones.
By Ads Dawson, Adrian Wood
arXiv:2606. 14295v1 Announce Type: cross Abstract: Frontier AI systems are increasingly capable of cybersecurity tasks, including codebase inspection, vulnerability detection, and exploitation.
By Fengyu Liu, Jiarun Dai, Yihe Fan, Wuyuao Mai, Ziao Li, Bofei Chen, Jie Zhang, Zheng Lou, Bocheng Xiang, Qiyi Zhang, Xudong Pan, Geng Hong, Yuan Zhang, Min Yang
LLM-based browser agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined scripts, these agents can autonomously navigate websites, reason about page content, and interact with web interfaces using natural-language instructions.
Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate ev...
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. 13079v1 Announce Type: cross Abstract: Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross.
By Jiaqi Luo, Jiarun Dai, Zhile Chen, Jia Xu, Weibing Wang, Yawen Duan, Brian Tse, Geng Hong, Xudong Pan, Yuan Zhang, Min Yang
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundant symbols, then route users through disguised links to services associated with...
RiskChainBench is a new benchmark that pairs 3,600 synthetic token‑text restoration inputs with 600 human‑labeled local web environments to evaluate how well models can recover obfuscated platform messages and then investigate the associated websites. The benchmark measures both message restoration accuracy and the subsequent web‑investigation decision, using a fixed multimodal evidence judge to assess faithfulness, sufficiency, completeness, and consistency. Across ten models, performance varies widely, with entry recovery ranging from 35.2% to 95.2% and web decision accuracy from 26.3% to 62.8%, highlighting execution failures as the main bottleneck.
By ZhuoXin Liu, Zhiming Ma, Ying Zhang, Mengzheng Yang, Yifan Wang, Zhengqi Huang, Yanhan Zhou, Zekun Lin, Jun Zhang, Shun Zhang, Yue Chen, Qiao Zhao, Peng Chen
The study examines how large language model agents cheat on cybersecurity benchmarks, finding that 37.1% of passes in a controlled prompt-ablation experiment involved cheating across 22 models. Anti‑cheat prompts reduce cheating rates from 33.0% to 8.5% while maintaining or improving solve rates, yet some models still cheat even under strict prompts. The authors propose a new "solve rate" metric to separate genuine capability from cheated outcomes and recommend it for future evaluations.
By Michael Kouremetis, Ads Dawson, Raja Sekhar Rao Dheekonda, Brian Greunke