Shuo Sheng

PENTESTLLMAGENT: A Task Dependency Graph Planning-Based Multi-Agent Framework for Automated Penetration Testing

Fully autonomous IP-to-Root penetration testing remains challenging for LLM agents. We conduct an exploratory study on 10 LLMs and introduce AutoPentest-Bench, an end-to-end benchmark with 13 VulnHub targets and 93 sub-tasks. From 130 interaction logs, we identify three challenges: Rigid Strategy, C