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

• URL: http://arxiv.org/abs/2605.06393v1
• Date: Thu, 07 May 2026 15:08:40 GMT
• Title: Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
• Abstract summary: Self-hosted computer-use agents (SHCUAs) combine natural-language interaction with direct access to host-side resources.<n>We present an operation-centric model for risk-based confinement of SHCUA operations.
• Score: 29.46902986541309
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• HazardAuditor: From Executable Threats to Safer Computer-Use Agents [50.06351661912873]
  Existing guard models target static prompts and responses.<n>Existing safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn.<n>We introduce HazardAuditor, an execution-grounded framework that closes both gaps.
  arXiv  Detail & Related papers  (2026-09-14T07:09:33Z)
• RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control [29.46902986541309]
  Natural-language control offers a promising interface for unmanned aerial vehicles (UAVs)<n>But directly applying self-hosted computer-use agents (SHCUAs) to UAV control introduces a structural mismatch.<n>This paper proposes a real-time and security-oriented restructuring of SHCUA-based UAV control.
  arXiv  Detail & Related papers  (2026-07-20T13:52:24Z)
• SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents [87.26967184869198]
  SeClaw is a framework that combines specification-driven security task synthesis with execution-based security evaluation for Autonomous agents.<n> benchmark covers risks arising from resources, user tasks, environments, and intrinsic agent behaviors.
  arXiv  Detail & Related papers  (2026-06-01T14:23:42Z)
• SafeAgent: A Runtime Protection Architecture for Agentic Systems [4.4767259565994495]
  This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem.<n>The proposed design separates execution governance from semantic risk reasoning through two coordinated components.<n> Experiments on Agent Security Bench (ASB) and InjecAgent show that SafeAgent consistently improves robustness over baseline and text-level guardrail methods.
  arXiv  Detail & Related papers  (2026-04-19T18:02:21Z)
• CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution [1.9473631530390483]
  CapSeal is a capability-sealed secret mediation architecture that replaces direct secret access with constrained invocations through a local trusted broker.<n>We describe a Rust prototype integrated with an MCP-facing adapter, formulate conditional security goals for non-disclosure, constrained use, replay resistance, and auditability.
  arXiv  Detail & Related papers  (2026-04-18T00:23:32Z)
• ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection [8.627671856044527]
  textscClawGuard enforces a user-confirmed rule set at every tool-call boundary.<n>textscClawGuard blocks all three injection pathways without model modification or infrastructure change.<n>This work establishes deterministic tool-call boundary enforcement as an effective defense mechanism for secure agentic AI systems.
  arXiv  Detail & Related papers  (2026-04-13T17:55:11Z)
• OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents [6.185334606321749]
  We present OpenClaw PRISM, a zero-fork runtime security layer for OpenClaw-based agent gateways.<n>PRISM combines an in-process plugin with optional sidecar services and distributes enforcement across ten lifecycle hooks.<n>We outline an evaluation methodology and benchmark pipeline for measuring security effectiveness, false positives, layer contribution, runtime overhead, and operational recoverability in an agent-runtime setting.
  arXiv  Detail & Related papers  (2026-03-12T12:20:12Z)
• OAMAC: Origin-Aware Mandatory Access Control for Practical Post-Compromise Attack Surface Reduction [0.0]
  Execution origin is a missing abstraction in modern operating system security models.<n>We introduce origin-aware mandatory access control (OAMAC)<n> OAMAC treats execution origin as a first-class security attribute.
  arXiv  Detail & Related papers  (2026-01-20T14:40:26Z)
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents [60.98294016925157]
  AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss.<n>We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content.<n>Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks.
  arXiv  Detail & Related papers  (2026-01-14T23:06:35Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Progent: Programmable Privilege Control for LLM Agents [46.31581986508561]
  We introduce Progent, the first privilege control framework to secure Large Language Models agents.<n>Progent enforces security at the tool level by restricting agents to performing tool calls necessary for user tasks while blocking potentially malicious ones.<n>Thanks to our modular design, integrating Progent does not alter agent internals and only requires minimal changes to the existing agent implementation.
  arXiv  Detail & Related papers  (2025-04-16T01:58:40Z)
• HasTEE+ : Confidential Cloud Computing and Analytics with Haskell [50.994023665559496]
  Confidential computing enables the protection of confidential code and data in a co-tenanted cloud deployment using specialized hardware isolation units called Trusted Execution Environments (TEEs) TEEs offer low-level C/C++-based toolchains that are susceptible to inherent memory safety vulnerabilities and lack language constructs to monitor explicit and implicit information-flow leaks. We address the above with HasTEE+, a domain-specific language (cla) embedded in Haskell that enables programming TEEs in a high-level language with strong type-safety.
  arXiv  Detail & Related papers  (2024-01-17T00:56:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.