MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
Abstract
LLMs are increasingly deployed as autonomous agents with access to tools, databases, and external services, yet practitioners (across different sectors) lack systematic methods to assess how known threat classes translate into concrete risks within a specific agentic deployment. We present MATRA, a pragmatic threat modeling framework for agentic AI systems that adapts established risk assessment methodology to systematically assess how known LLM threats translate into deployment-specific risks. MATRA begins with an asset-based impact assessment and utilizes attack trees to determine the likelihood of these impacts occurring within the system architecture. We demonstrate MATRA on a personal AI agent deployment using OpenClaw, quantifying how architectural controls such as network sandboxing and least-privilege access reduce risk by limiting the blast radius of successful injections.
Keywords
Cite
@article{arxiv.2605.10763,
title = {MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study},
author = {Tim Van hamme and Thomas Vissers and Javier Carnerero-Cano and Mario Fritz and Emil C. Lupu and Lieven Desmet and Dinil Mon Divakaran},
journal= {arXiv preprint arXiv:2605.10763},
year = {2026}
}
Comments
Accepted for presentation at the 5th International Workshop on Designing and Measuring Security in Systems with AI (DeMeSSAI 2026), co-located with the 11th IEEE European Symposium on Security and Privacy (EuroS&P 2026), Lisbon, Portugal, July 10, 2026