Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Exploiting LLM Agent Supply Chains via Payload-less Skills
Xinyu Liu, Yukai Zhao, Xing Hu +1
Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations br…
cs.CR2026
Triggering and Detecting Exploitable Library Vulnerability from the Client by Directed Greybox Fuzzing
Yukai Zhao, Menghan Wu, Xing Hu +3
Developers utilize third-party libraries to improve productivity, which also introduces potential security risks. Existing approaches generate tests for public functions to trigger…