Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
Coding agents powered by large language models are becoming central modules of modern IDEs. They help users to perform various complex coding tasks by invoking tools. Although powerful, tool-invocation operation in coding agents opens a substantial attack surface for adversaries. Prior work has demonstrated attacks aga...
Yuchong Xie, Mingyu Luo, Zesen Liu et al.
· Proceedings of the ACM on so... · 0 citations