works on

From the 2 of 8 linked papers with an AI index.

collaborators

8 papers

cs.CR2026

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

Yihao Zhang, Zeming Wei, Xiaokun Luan +7

The paper introduces AgentWorm, a self-replicating worm that can autonomously infect and spread across large-scale LLM-based agent ecosystems by hijacking configurations and execut…

cs.SE2026

FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse

Yiming Zhang, Jiangrong Wu, Yuhong Nan

FlowArk is a system that lets code‑analysis agents reuse knowledge from earlier data‑flow analyses of Android apps, cutting redundant work and lowering API costs while keeping anal…

cs.CR2026

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…

cs.CR2026

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…

cs.CR2026

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…

cs.SE2026

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents

Jiangrong Wu, Zitong Yao, Yuhong Nan +1

Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool ca…