Lei Ma
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Document-Driven Implicit Payload Execution (DDIPE) to demonstrate that malicious code can be embedded in LLM agent skill documentation, allowing supply-chain attacks to hijack agent actions without explicit prompts.
This study conducts a large-scale empirical analysis of third-party LLM agent skills, identifying that credential leakage is a pervasive, cross-modal issue primarily caused by debug logging and resulting in exploitable, persistent secrets.
The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sampled trajectories are uniformly correct or incorrect.
This paper shows that large language models can automate reproducibility assessments in the social and behavioral sciences.