English
Related papers

Related papers: AgentTrap: Measuring Runtime Trust Failures in Thi…

200 papers

Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security…

Artificial Intelligence · Computer Science 2026-01-14 Xinyi Wu , Jiagui Chen , Geng Hong , Jiayi Dong , Xudong Pan , Jiarun Dai , Min Yang

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from…

Cryptography and Security · Computer Science 2026-01-19 Fengchao Chen , Tingmin Wu , Van Nguyen , Carsten Rudolph

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates…

Cryptography and Security · Computer Science 2026-02-25 Julia Bazinska , Max Mathys , Francesco Casucci , Mateo Rojas-Carulla , Xander Davies , Alexandra Souly , Niklas Pfister

LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture…

Software Engineering · Computer Science 2026-05-28 Yipeng Ouyang , Xin Huang , Bingjie Liu , Zhongchun Zheng , Yuhao Gu , Xianwei Zhang

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…

Artificial Intelligence · Computer Science 2025-08-19 Ruofan Lu , Yichen Li , Yintong Huo

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Cryptography and Security · Computer Science 2026-04-08 Zenghao Duan , Yuxin Tian , Zhiyi Yin , Liang Pang , Jingcheng Deng , Zihao Wei , Shicheng Xu , Yuyao Ge , Xueqi Cheng

We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…

Cryptography and Security · Computer Science 2026-05-26 Peiran Wang , Ying Li , Yuan Tian

The potential of Large Language Model (LLM) as agents has been widely acknowledged recently. Thus, there is an urgent need to quantitatively \textit{evaluate LLMs as agents} on challenging tasks in interactive environments. We present…

When an LLM agent reads a confidential file, then writes a summary, then emails it externally, no single step is unsafe, but the sequence is a data leak. We call this safety drift: individually safe actions compounding into violations.…

Cryptography and Security · Computer Science 2026-03-31 Aditya Dhodapkar , Farhaan Pishori

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…

Cryptography and Security · Computer Science 2026-05-22 Jianan Ma , Xiaohu Du , Ruixiao Lin , Yaoxiang Bian , Jialuo Chen , Jingyi Wang , Xiaofang Yang , Shiwen Cui , Changhua Meng , Xinhao Deng , Zhen Wang

Tabletop exercises are a crucial component of many company's strategy to test and evaluate its preparedness for security incidents in a realistic way. Traditionally led by external firms specializing in cybersecurity, these exercises can be…

Cryptography and Security · Computer Science 2024-08-31 Sam Hays , Jules White

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Cryptography and Security · Computer Science 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

Cryptography and Security · Computer Science 2026-05-13 Yassin H. Rassul , Tarik A. Rashid

Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or…

Cryptography and Security · Computer Science 2026-04-13 Guiyao Tie , Jiawen Shi , Pan Zhou , Lichao Sun

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

Information Retrieval · Computer Science 2026-05-27 Yingli Zhou , Wang Shu , Yaodong Su , Wenchuan Du , Yixiang Fang , Xuemin Lin

Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill…

Computation and Language · Computer Science 2026-05-29 Jiahao Ying , Boxian Ai , Wei Tang , Siyuan Liu , Yixin Cao

As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…

Artificial Intelligence · Computer Science 2026-04-02 Chris Ge , Daria Kryvosheieva , Daniel Fried , Uzay Girit , Kaivalya Hariharan

Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…

Artificial Intelligence · Computer Science 2025-08-01 Haoyu Wang , Christopher M. Poskitt , Jun Sun

Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem,…

Cryptography and Security · Computer Science 2026-04-06 Zhihao Chen , Ying Zhang , Yi Liu , Gelei Deng , Yuekang Li , Yanjun Zhang , Jianting Ning , Leo Yu Zhang , Lei Ma , Zhiqiang Li

LLM applications (i.e., LLM apps) leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional application development. While the increasing prevalence of LLM-powered applications…

Cryptography and Security · Computer Science 2025-12-17 Yunyi Zhang , Shibo Cui , Baojun Liu , Jingkai Yu , Min Zhang , Fan Shi , Han Zheng