Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Di, Zhang, Bo, Li, Xiyuan, Liao, Yongzhi, Dong, Xuewen, Shen, Yulong, Liu, Zhiquan, Ma, Jianfeng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914539715428352
author Lu, Di
Zhang, Bo
Li, Xiyuan
Liao, Yongzhi
Dong, Xuewen
Shen, Yulong
Liu, Zhiquan
Ma, Jianfeng
author_facet Lu, Di
Zhang, Bo
Li, Xiyuan
Liao, Yongzhi
Dong, Xuewen
Shen, Yulong
Liu, Zhiquan
Ma, Jianfeng
contents Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including browsers, files, scripts, system commands, and external communication channels. While useful for automating real tasks, this capability also creates a host-level abuse surface: a legitimately deployed agent may be steered toward unsafe operations through malicious messages, indirect prompt injection, unsafe skills, or tampering along the host-side control path. We argue that such risks cannot be addressed by ad hoc blocking rules alone, because the security criticality of an operation depends jointly on its action type, target object, execution context, and potential effect. This paper presents an operation-centric model for risk-based confinement of SHCUA operations. The proposed design keeps ordinary functionality on the constrained REE path, while protecting security-critical classification, authorization, binding, evidence generation, and selected execution-control decisions inside a cloud-native TEE-backed trusted operation plane. We instantiate the architecture on OpenClaw using Intel TDX as the primary trusted backend, with remote terminal-side trusted components verifying TDX-audited commands before constrained local execution. The evaluation shows that the design can block unsafe or policy-disallowed operations before execution, preserve ordinary functionality for allowed workloads, and provide auditable evidence with deployment-dependent overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06393
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
Lu, Di
Zhang, Bo
Li, Xiyuan
Liao, Yongzhi
Dong, Xuewen
Shen, Yulong
Liu, Zhiquan
Ma, Jianfeng
Cryptography and Security
Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including browsers, files, scripts, system commands, and external communication channels. While useful for automating real tasks, this capability also creates a host-level abuse surface: a legitimately deployed agent may be steered toward unsafe operations through malicious messages, indirect prompt injection, unsafe skills, or tampering along the host-side control path. We argue that such risks cannot be addressed by ad hoc blocking rules alone, because the security criticality of an operation depends jointly on its action type, target object, execution context, and potential effect. This paper presents an operation-centric model for risk-based confinement of SHCUA operations. The proposed design keeps ordinary functionality on the constrained REE path, while protecting security-critical classification, authorization, binding, evidence generation, and selected execution-control decisions inside a cloud-native TEE-backed trusted operation plane. We instantiate the architecture on OpenClaw using Intel TDX as the primary trusted backend, with remote terminal-side trusted components verifying TDX-audited commands before constrained local execution. The evaluation shows that the design can block unsafe or policy-disallowed operations before execution, preserve ordinary functionality for allowed workloads, and provide auditable evidence with deployment-dependent overhead.
title Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
topic Cryptography and Security
url https://arxiv.org/abs/2605.06393