الباحثون

Juanjuan Zhao

المنشورات 1

نسخة أولية وصول مفتوح

A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem

Laizhen Li, Xuan Wang, Peicheng Zhao وآخرون · 2026

Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-controlled metadata and outputs. We introduce A2M (Attraction-to-Manipulation), a two-stage black-box framework for hijacking MCP agents. The Attractio …

المؤلفون المشاركون