5 papers · 1 filter
MOSAIC: Knowledge-Guided CLI Command Composition Attack in LLM Coding Agents
Jiangrong Wu, Huaijin Wang, Yihao Zhang +2
LLM coding agents increasingly complete development tasks by issuing ordinary CLI commands. Following the Unix design, these commands cooperate through shared operating-system stat…
SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
Jiangrong Wu, Yuhong Nan, Yixi Lin +4
Agent Skills have become a practical way to extend LLM agents by packaging metadata, natural-language instructions, and executable resources into reusable capability bundles. Howev…
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Yihao Zhang, Kai Wang, Jiangrong Wu +7
Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security constraints and generate unethical or u…
AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
Yihao Zhang, Zeming Wei, Xiaokun Luan +7
Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplore…
Your Mailbox Is Mine: Prompt Injection Attacks Against Real-World LLM Email Agents
Jiangrong Wu, Yuhong Nan, Jianliang Wu +4
Large Language Model (LLM) email agents have emerged as pivotal autonomous assistants, serving as a critical root of trust for digital identity by managing sensitive communications…