14 papers
Towards Security-Auditable LLM Agents: A Unified Graph Representation
Chaofan Li, Lyuye Zhang, Jintao Zhai +9
LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. Howev…
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…
Minimizing Breaking Changes and Redundancy in Mitigating Technical Lag for Java Projects
Rui Lu, Lyuye Zhang, Kaixuan Li +2
Re-using open-source software (OSS) can avoid reinventing the wheel, but failing to keep it up-to-date can lead to missing new features and persistent bugs or vulnerabilities that…
Real-World Usability of Vulnerability Proof-of-Concepts: A Comprehensive Study
Wenjing Dang, Kaixuan Li, Sen Chen +3
The Proof-of-Concept (PoC) for a vulnerability is crucial in validating its existence, mitigating false positives, and illustrating the severity of the security threat it poses. Ho…
A Systematic Study on Generating Web Vulnerability Proof-of-Concepts Using Large Language Models
Mengyao Zhao, Kaixuan Li, Lyuye Zhang +4
Recent advances in Large Language Models (LLMs) have brought remarkable progress in code understanding and reasoning, creating new opportunities and raising new concerns for softwa…
A Taxonomy of Prompt Defects in LLM Systems
Haoye Tian, Chong Wang, BoYang Yang +2
Large Language Models (LLMs) have become key components of modern software, with prompts acting as their de-facto programming interface. However, prompt design remains largely empi…