3 papers
cs.CR2026
MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
Wenbo Guo, Wei Zeng, Chengwei Liu +5
AI coding agents such as Claude Code and Gemini CLI increasingly extend themselves with third-party skills: markdown packages bundling natural-language instructions, executable scr…
cs.AI2025
The Agent Behavior: Model, Governance and Challenges in the AI Digital Age
Qiang Zhang, Pei Yan, Yijia Xu +3
Advancements in AI have led to agents in networked environments increasingly mirroring human behavior, thereby blurring the boundary between artificial and human actors in specific…
cs.CR2024
SpearBot: Leveraging Large Language Models in a Generative-Critique Framework for Spear-Phishing Email Generation
Qinglin Qi, Yun Luo, Yijia Xu +2
Large Language Models (LLMs) are increasingly capable, aiding in tasks such as content generation, yet they also pose risks, particularly in generating harmful spear-phishing email…