Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

• URL: http://arxiv.org/abs/2608.02018v2
• Date: Thu, 06 Aug 2026 02:33:08 GMT
• Title: Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents
• Abstract summary: We present II-Bench, a collection of seemingly harmless adversarial tasks.<n>II-Bench comprises 444 examples targeting confidentiality and integrity attacks across three platforms.<n>We also construct HITLCUA, a comprehensive adversarial testing framework.
• Score: 10.553545687886928
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer-use agents (CUAs), which empower large language models to autonomously operate operating systems and the web, are increasingly vulnerable to indirect prompt injection attacks. A widely adopted defense is the human-in-the-loop paradigm, in which the agent pauses for explicit user confirmation before executing sensitive operations. While effective against conspicuously high-harm attacks, this defense offers little protection against what we term Invisible Ink Threats: low-harm injected goals, such as starring a repository or installing a package, that are behaviorally indistinguishable from legitimate task execution and thus evade both model safety mechanisms and human oversight. To systematically investigate this blind spot, we present II-Bench, a collection of seemingly harmless adversarial tasks. II-Bench comprises 444 examples targeting confidentiality and integrity attacks across three platforms, spanning three attack categories: page navigation and interaction, sensitive information exfiltration, and code download and execution. Each category is instantiated in both natural language and code forms under two levels of instruction specificity. Furthermore, we construct HITLCUA, a comprehensive adversarial testing framework that integrates a real virtual machine operating system environment with isolated Docker-based web platforms, and simulates human participation by allowing CUAs to consult an API-simulated user before proceeding with suspicious operations. Extensive evaluations of leading CUAs reveal that low-harm injections frequently bypass both agent defenses and simulated user review, exposing severe and previously underexplored security risks in current CUAs.

Related papers

• SIR: Self-improving Red-teaming for Compute Use Agents [71.71987044117371]
  Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal.<n>Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI)<n>We present SIR, a black box IPI attack that composes stealthy injections from a small library of reusable principles stated in plain language.
  arXiv  Detail & Related papers  (2026-08-31T03:39:43Z)
• MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents [74.64265314956441]
  We propose a unified black-box attack framework that poisons graph-structured external memory with coordinated text-image evidence.<n>MemVenom achieves strong end-to-end attack success with minimal impact on benign performance, reaching up to 99.15% on GPT-5-family web agents.
  arXiv  Detail & Related papers  (2026-06-09T11:53:25Z)
• WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents [117.65855863464863]
  Web agents are highly vulnerable to prompt injection attacks.<n>Existing defenses, including system prompt defenses and direct fine-tuning of agents, have shown limited effectiveness.<n>We introduce WebAgentGuard, a reasoning-driven, multimodal guard model for prompt injection detection.
  arXiv  Detail & Related papers  (2026-04-14T04:50:35Z)
• MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks [10.431616150153992]
  MUZZLE is an automated framework for evaluating the security of web agents against indirect prompt injection attacks.<n>It adapts its attack strategy based on the agent's observed execution trajectory and iteratively refines attacks using feedback from failed executions.<n>MUZZLE effectively discovers 37 new attacks on 4 web applications with 10 adversarial objectives that violate confidentiality, availability, or privacy properties.
  arXiv  Detail & Related papers  (2026-02-09T21:46:18Z)
• Cuckoo Attack: Stealthy and Persistent Attacks Against AI-IDE [64.47951172662745]
  Cuckoo Attack is a novel attack that achieves stealthy and persistent command execution by embedding malicious payloads into configuration files.<n>We formalize our attack paradigm into two stages, including initial infection and persistence.<n>We contribute seven actionable checkpoints for vendors to evaluate their product security.
  arXiv  Detail & Related papers  (2025-09-19T04:10:52Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• 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)
• Context manipulation attacks : Web agents are susceptible to corrupted memory [37.66661108936654]
  "Plan injection" is a novel context manipulation attack that corrupts these agents' internal task representations by targeting this vulnerable context.<n>We show that plan injections bypass robust prompt injection defenses, achieving up to 3x higher attack success rates than comparable prompt-based attacks.<n>Our findings highlight that secure memory handling must be a first-class concern in agentic systems.
  arXiv  Detail & Related papers  (2025-06-18T14:29:02Z)
• VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents [74.6761188527948]
  Computer-Use Agents (CUAs) with full system access pose significant security and privacy risks.<n>We investigate Visual Prompt Injection (VPI) attacks, where malicious instructions are visually embedded within rendered user interfaces.<n>Our empirical study shows that current CUAs and BUAs can be deceived at rates of up to 51% and 100%, respectively, on certain platforms.
  arXiv  Detail & Related papers  (2025-06-03T05:21:50Z)
• The Hidden Dangers of Browsing AI Agents [0.0]
  This paper presents a comprehensive security evaluation of such agents, focusing on systemic vulnerabilities across multiple architectural layers.<n>Our work outlines the first end-to-end threat model for browsing agents and provides actionable guidance for securing their deployment in real-world environments.
  arXiv  Detail & Related papers  (2025-05-19T13:10:29Z)
• Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection [67.53296659361598]
  adversarial EXEmples can bypass machine learning-based detection by perturbing relatively few input bytes. We develop a unifying framework that does not only encompass and generalize previous attacks against machine-learning models, but also includes three novel attacks. These attacks, named Full DOS, Extend and Shift, inject the adversarial payload by respectively manipulating the DOS header, extending it, and shifting the content of the first section.
  arXiv  Detail & Related papers  (2020-08-17T07:16:57Z)

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.