Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent

• URL: http://arxiv.org/abs/2510.06607v2
• Date: Thu, 09 Oct 2025 18:18:19 GMT
• Title: Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent
• Authors: Weidi Luo, Qiming Zhang, Tianyu Lu, Xiaogeng Liu, Bin Hu, Hung-Chun Chiu, Siyuan Ma, Yizhe Zhang, Xusheng Xiao, Yinzhi Cao, Zhen Xiang, Chaowei Xiao,
• Abstract summary: We propose AdvCUA, the first benchmark aligned with real-world TTPs in MITRE ATT&CK Enterprise Matrix.<n>We evaluate the existing five mainstream CUAs, including ReAct, AutoGPT, Gemini CLI, and Cursor CLI.<n>Results demonstrate that current frontier CUAs do not adequately cover OS security-centric threats.
• Score: 64.08182031659047
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most critical applications is operating system (OS) control. As CUAs in the OS domain become increasingly embedded in daily operations, it is imperative to examine their real-world security implications, specifically whether CUAs can be misused to perform realistic, security-relevant attacks. Existing works exhibit four major limitations: Missing attacker-knowledge model on tactics, techniques, and procedures (TTP), Incomplete coverage for end-to-end kill chains, unrealistic environment without multi-host and encrypted user credentials, and unreliable judgment dependent on LLM-as-a-Judge. To address these gaps, we propose AdvCUA, the first benchmark aligned with real-world TTPs in MITRE ATT&CK Enterprise Matrix, which comprises 140 tasks, including 40 direct malicious tasks, 74 TTP-based malicious tasks, and 26 end-to-end kill chains, systematically evaluates CUAs under a realistic enterprise OS security threat in a multi-host environment sandbox by hard-coded evaluation. We evaluate the existing five mainstream CUAs, including ReAct, AutoGPT, Gemini CLI, Cursor CLI, and Cursor IDE based on 8 foundation LLMs. The results demonstrate that current frontier CUAs do not adequately cover OS security-centric threats. These capabilities of CUAs reduce dependence on custom malware and deep domain expertise, enabling even inexperienced attackers to mount complex enterprise intrusions, which raises social concern about the responsibility and security of CUAs.

Related papers

• LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios [51.52395368061729]
  We present LPS-Bench, a benchmark that evaluates the planning-time safety awareness of MCP-based CUAs under long-horizon tasks.<n> Experiments reveal substantial deficiencies in existing CUAs' ability to maintain safe behavior.<n>We propose mitigation strategies to improve long-horizon planning safety in MCP-based CUA systems.
  arXiv  Detail & Related papers  (2026-02-03T08:40:24Z)
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents [60.98294016925157]
  AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss.<n>We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content.<n>Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks.
  arXiv  Detail & Related papers  (2026-01-14T23:06:35Z)
• STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents [38.755035623707656]
  This paper introduces Sequential Tool Attack Chaining (STAC), a novel multi-turn attack framework that exploits agent tool use.<n>We apply our framework to automatically generate and evaluate 483 STAC cases, featuring 1,352 sets of user-agent-environment interactions.<n>Our evaluations show that state-of-the-art LLM agents, including GPT-4.1, are highly vulnerable to STAC, with attack success rates (ASR) exceeding 90% in most cases.
  arXiv  Detail & Related papers  (2025-09-30T00:31:44Z)
• Secure and Efficient Access Control for Computer-Use Agents via Context Space [11.077973600902853]
  CSAgent is a system-level, static policy-based access control framework for computer-use agents.<n>We implement and evaluate CSAgent, which successfully defends against more than 99.36% of attacks while introducing only 6.83% performance overhead.
  arXiv  Detail & Related papers  (2025-09-26T12:19:27Z)
• AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents [7.99316950952212]
  Large Language Models (LLMs) have been increasingly integrated into computer-use agents.<n>LLMs may issue unintended tool commands or incorrect inputs, leading to potentially harmful operations.<n>We propose AgentSentinel, an end-to-end, real-time defense framework designed to mitigate potential security threats.
  arXiv  Detail & Related papers  (2025-09-09T13:59:00Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• A Systematization of Security Vulnerabilities in Computer Use Agents [1.3560089220432787]
  We conduct a systematic threat analysis and testing of real-world CUAs under adversarial conditions.<n>We identify seven classes of risks unique to the CUA paradigm, and analyze three concrete exploit scenarios in depth.<n>These case studies reveal deeper architectural flaws across current CUA implementations.
  arXiv  Detail & Related papers  (2025-07-07T19:50:21Z)
• RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments [40.354694210052095]
  Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection.<n>We propose RedTeamCUA, an adversarial testing framework featuring a novel hybrid sandbox that integrates a VM-based OS environment with Docker-based web platforms.<n>RedTeamCUA provides an essential framework for advancing realistic, controlled, and systematic analysis of CUA vulnerabilities.
  arXiv  Detail & Related papers  (2025-05-28T03:42:09Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Defeating Prompt Injections by Design [79.00910871948787]
  CaMeL is a robust defense that creates a protective system layer around the Large Language Models.<n>To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query.<n>To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows.
  arXiv  Detail & Related papers  (2025-03-24T15:54:10Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.