4 papers
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
Zonghao Ying, Xiangfan Wu, Huiyu Wu +4
Self-evolving agents increasingly convert interaction histories into reusable skills that persist beyond individual tasks. While prior work studies memory and retrieval poisoning,…
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
Yong Yang, Xing Zheng, Huiyu Wu +7
The fast growth of open-source AI infrastructure, from model serving engines and agent platforms to the Model Context Protocol (MCP) ecosystem and the language models themselves, h…
PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
Zichao Wei, Jun Zeng, Ming Wen +8
Software vulnerabilities are increasing at an alarming rate. However, manual patching is both time-consuming and resource-intensive, while existing automated vulnerability repair (…
MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers
Bin Wang, Zexin Liu, Hao Yu +6
The Model Context Protocol (MCP) has emerged as a standardized interface enabling seamless integration between Large Language Models (LLMs) and external data sources and tools. Whi…