Securing Computer-Use Agents Against Branch Steering Attacks

A 2 October 2026 arXiv paper introduces STEER-Bench, a 101-task benchmark across 9 domains, and reports that branch steering attacks succeed against 94.4% of standard Computer Use Agents and 89.5% of vanilla Dual-LLM CUAs. The authors propose COBRA, an architecture pairing trusted branching plans with ahead-of-time capability constraints that bound each branch's parameters and destinations, which cuts attack success to 0% on STEER-Bench while retaining 97% benign utility.

Computer Science Cryptography and Security Submitted on 2 Oct 2026 Title:Securing Computer-Use Agents Against Branch Steering Attacks View PDF https://arxiv.org/pdf/2610.03089 HTML experimental https://arxiv.org/html/2610.03089v1 Abstract: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 guarantees - using an isolated Planner LLM P-LLM to fix execution paths before processing untrusted inputs via a Quarantined LLM Q-LLM - these guarantees break down in graphical environments. Because CUA interaction is inherently dynamic, plans cannot remain data-independent; they must branch based on anticipated runtime web content - covering all possible cases the agent may encounter. This exposes agents to branch steering attacks, where an adversary crafts untrusted data to coerce a CUA down a hazardous, pre-approved branch without injecting explicit instructions. We systematically study branch steering attacks and introduce STEER-Bench 101 tasks across 9 domains , showing high attack success against both standard 94.4% and vanilla Dual-LLM 89.5% CUAs. We then propose COBRA, an architecture that pairs trusted branching plans with ahead-of-time capability constraints, strictly bounding the parameters and destinations each branch may execute. On STEER-Bench, COBRA reduces attack success to 0% while retaining 97% benign utility. References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .