From the 1 of 16 linked papers with an AI index.
16 papers
Implicit, Yet Impactful: Understanding Hidden Dependencies in Java Projects
Lyuye Zhang, Chengwei Liu, Fangyuan Zhang +3
As software usage continues to expand, package managers automatically resolve dependencies to construct a dependency graph based on user-specified requirements. These explicitly de…
Mutate to Bypass: Autonomous Endpoint Evasion via Knowledge-Driven Multi-Agent Orchestration
Weifeng Yuan, Wenbo Guo, Qingyun Du +4
Public reports and open-source resources expose many EDR evasion techniques, but it remains unclear whether commercial Endpoint Detection and Response (EDR) systems can withstand t…
Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents
Weifeng Yuan, Wenbo Guo, Feng Dong +2
The paper investigates how large language model agents often fabricate nonexistent skill names when asked to recommend and install skills, exposing a supply‑chain security risk, an…
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…
How Effective Are NPM Malicious Package Detectors? A Large-Scale Empirical Study
Wenbo Guo, Zhongwen Chen, Zhengzi Xu +7
The NPM ecosystem faces escalating threats from malicious packages that exploit its open publication model. While numerous detection tools have been proposed, they are evaluated on…
Latent Reuse in Agent Skills: Multi-modal Clone Detection at Ecosystem Scale
Jiaying Zhu, Lyuye Zhang, Wenbo Guo +1
An agent skill is a reusable package for extending an LLM agent, typically a SKILL.md file that combines YAML metadata, natural-language instructions, and executable code. Public r…