Xin Huang

This paper analyzes the security vulnerabilities of the Model Context Protocol (MCP), identifying tool poisoning as the most critical client-side threat, and proposes a multi-layered defense strategy.

The paper empirically analyzes the susceptibility of seven widely used AI-assisted development tools (MCP clients) to prompt injection via tool-poisoning, revealing significant disparities in their security guardrails.

The paper introduces mcp-sec-audit, a comprehensive toolkit that assesses Model Context Protocol (MCP) servers for over-privileged and insecure tool capabilities.

The paper introduces a diagnostic testbed, PAVE, to evaluate how LLMs arbitrate between their internal knowledge and retrieved evidence during fact-checking, revealing that this arbitration is unreliable and highly model-dependent.

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.