arXiv Brief — 2026-09-16
LLM agents are central today, revealing new architectural risks like capability laundering and the stochastic deputy problem, while hardware vulnerabilities expand into GPU memory architectures.
Llm-Security
Architectural Evaluation of Virtualization and Sandbox Technologies for Custom MCP-Driven Autonomous Malware Analysis
A feasibility study and architectural blueprint for integrating an LLM agent via a custom Model Context Protocol (MCP) server to dynamically orchestrate and steer malware execution across diverse virtualization technologies.
arXiv Brief — 2026-09-15
New perspectives on LLM agent security: a census of the Model Context Protocol ecosystem, attacks via gated memories and contextual bias, new attacks on agent architectures, and LLM-guided smart contract fuzzing.