cua-kit

CUA-Kit A toolkit for enumerating and interacting with computer use agents on Windows and macOS systems. Tools Tool| Description| Outputs ---|---|--- cua-enum| Enumerate computer use agent configurations Claude Code, Codex CLI, Cursor, Gemini CLI| .exe, .x64.o cua-exec| Execute computer use agent...

CUAHarm

Measuring Harmfulness of Computer-Using Agents 🤗 Hugging Face 📄 Paper 📋 Introduction CUAHarm is a benchmark designed to evaluate the safety risks of Computer-Using Agents CUAs - AI agents that can autonomously control computers to perform multi-step actions. Key Features 🔍 CUAHarm Dataset : A...

Securing Computer-Use Agents against Branch Steering Attacks

Modern Computer Use Agents CUAs directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt injection across every rendered page and tool response. While the Dual-LLM pattern is the primary system-level architecture offering formal security...

ZoneClaw: Mitigating Persistent Memory Attacks by Establishing Memory-Zoning in OpenClaw-Style Computer-Use Agents

Computer-use agents increasingly operate as long-running assistants through persistent workspace memory, which OpenClaw-style CUAs realize as automatically reloaded files that hold user instructions, system summaries, and external claims at the same privilege level. Here, remembering a claim...

AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents

This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents CUAs. The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing...

SIR: Self-Improving Red-Teaming for Compute Use Agents

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 everyday digital tasks. Because they can be exposed to untrusted content while operating, they are...

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

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 confirmati...

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, moder...

AgentSentinel: an End-To-End and Real-Time Security Defense Framework for Computer-Use Agents

Large Language Models LLMs have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature of LLM outputs, they may issue unintended tool commands or...

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents

Computer-Use Agents CUAs with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work has focused on browser-based agents and HTML-level attacks,...