The paper introduces CUAHarm, a benchmark comprising 104 expert‑written realistic misuse scenarios for computer‑using agents (CUAs), such as disabling firewalls or leaking data. Using a sandbox with verifiable rewards, the authors evaluate frontier language models—including GPT‑5, Claude 4 Sonnet, Gemini 2.5 Pro, Llama‑3.3‑70B, and Mistral Large 2—and find that even without jailbreak prompts, these models can successfully execute many malicious tasks at high rates (e.g., 90% for Gemini 2.5 Pro). The study also shows that newer models, while safer in traditional safety benchmarks, exhibit higher misuse risks as CUAs, and that monitoring CUAs’ actions remains challenging, with current methods achieving only about 77% accuracy.
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...
arXiv:2604. 07223v2 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces.
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
The paper introduces a unified framework for monitoring misuse of large language model agents in multi‑actor settings, focusing on two attack types: decomposition attacks and prompt injection attacks. It proposes tracking the agent’s externalised actions and determining whether the first detection of harm falls within a defined harm window. Using this formalism, the authors build a benchmark of about 6,200 conversation transcripts and evaluate 17 monitor configurations, finding that action‑framed monitors perform well on both threats while content‑framed monitors struggle with injection attacks, and highlighting limitations of traditional position‑blind metrics.
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
arXiv:2509. 25624v3 Announce Type: replace-cross Abstract: As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns.
arXiv:2607. 26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.
arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a...
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.
arXiv:2606.23189v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-appl...
APEX-Harm is a benchmark that tests prompt and script injection attacks on long‑horizon agents working in large, shared professional workspaces. The benchmark covers finance, consulting, and legal tasks, each involving 115–328 files and multiple tools such as email, calendar, chat, documents, spreadsheets, PDFs, and code execution. It evaluates six attack categories and measures attack success, exposure, and task performance across 12 frontier models, revealing that many agents can complete tasks while still executing unauthorized actions.
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...