Year: 2026
Type: preprint
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.
Source: arXiv (Cornell University)
Institution: KU Leuven
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: KU Leuven, Vlaamse regering
OpenAlex ID: W7160948959