Yiyong Liu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1
Frequent co-authors
Research Timeline
2026
Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
This paper introduces Dependency Steering, a novel attack paradigm demonstrating that malicious agent skills can actively bias LLM coding agents to use attacker-controlled packages, posing a significant, hard-to-detect software supply chain risk.
Highlighted terms show continued research focus across papers
Papers
cs.CRRecentMay 10, 2026
Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
Yiyong Liu, Chia-Yi Hsu, Chun-Ying Huang, Michael Backes +2 more
This paper introduces Dependency Steering, a novel attack paradigm demonstrating that malicious agent skills can actively bias LLM coding agents to use attacker-controlled packages, posing a significa…
View →