# A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

arXiv: https://arxiv.org/abs/2505.10924 · HTML: https://mlsanity.com/paper/2505.10924/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 75 of its 128 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 30 of 75)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [You Only Look at Screens: Multimodal Chain-of-Action Agents](https://mlsanity.com/paper/2309.11436/) (2023)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024)
- [ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning](https://mlsanity.com/paper/2503.22738/) (2025)
- [EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage](https://mlsanity.com/paper/2409.11295/) (2024)
- [AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://mlsanity.com/paper/2403.04783/) (2024)
- [AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents](https://mlsanity.com/paper/2406.13352/) (2024)
- [Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents](https://mlsanity.com/paper/2402.11208/) (2024)
- [ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents](https://mlsanity.com/paper/2410.06703/) (2024)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents](https://mlsanity.com/paper/2503.00061/) (2025)
- [Dissecting Adversarial Robustness of Multimodal LM Agents](https://mlsanity.com/paper/2406.12814/) (2024)

## Built on by (most cited first, 23 of 23)

- [From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows](https://mlsanity.com/paper/2506.23260/) (2025)
- [MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments](https://mlsanity.com/paper/2506.01616/) (2025)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness](https://mlsanity.com/paper/2510.01670/) (2025)
- [When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents](https://mlsanity.com/paper/2602.08995/) (2026)
- [Adaptive Vision-Language Model Routing for Computer Use Agents](https://mlsanity.com/paper/2603.12823/) (2026)
- [Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety](https://mlsanity.com/paper/2509.21782/) (2025)
- [From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents](https://mlsanity.com/paper/2606.05805/) (2026)
- [Mobile GUI Agents under Real-world Threats: Are We There Yet?](https://mlsanity.com/paper/2507.04227/) (2025)
- [Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness](https://mlsanity.com/paper/2510.08238/) (2025)
- [Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System](https://mlsanity.com/paper/2602.10915/) (2026)
- [FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight](https://mlsanity.com/paper/2602.11136/) (2026)
- [TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework](https://mlsanity.com/paper/2510.17163/) (2025)
- [When Convenience Becomes Risk: A Semantic View of Under-Specification in Host-Acting Agents](https://mlsanity.com/paper/2603.21231/) (2026)
- [Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming](https://mlsanity.com/paper/2606.05233/) (2026)
- [AutoRAS: Learning Robust Agentic Systems with Primitive Representations](https://mlsanity.com/paper/2606.21445/) (2026)
- [Semantic-aware Graph-guided Behavior Sequences Generation with Large Language Models for Smart Homes](https://mlsanity.com/paper/2508.03484/) (2025)
- [Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability](https://mlsanity.com/paper/2605.07110/) (2026)
- [Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents](https://mlsanity.com/paper/2605.29224/) (2026)
- [RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control](https://mlsanity.com/paper/2607.17951/) (2026)
- [Data Leakage Prevention in Agentic Applications via Preemptive Hardening](https://mlsanity.com/paper/2607.18847/) (2026)
- [Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing](https://mlsanity.com/paper/2607.21758/) (2026)
- [ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices](https://mlsanity.com/paper/2608.26204/) (2026)

## Abstract (arXiv)

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of Computer-Using Agents (CUAs), capable of autonomously performing tasks such as navigating desktop applications, web pages, and mobile apps. However, as these agents grow in capability, they also introduce novel safety and security risks. Vulnerabilities in LLM-driven reasoning, with the added complexity of integrating multiple software components and multimodal inputs, further complicate the security landscape. In this paper, we present a systematization of knowledge on the safety and security threats of CUAs. We conduct a comprehensive literature review and distill our findings along four research objectives: textit(i) define the CUA that suits safety analysis; textit(ii)  categorize current safety threats among CUAs; textit(iii) propose a comprehensive taxonomy of existing defensive strategies; textit(iv) summarize prevailing benchmarks, datasets, and evaluation metrics used to assess the safety and performance of CUAs. Building on these insights, our work provides future researchers with a structured foundation for exploring unexplored vulnerabilities and offers practitioners actionable guidance in designing and deploying secure Computer-Using Agents.