1
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing
解耦侦察与利用，精准测量LLM在渗透测试中的真实能力边界。
arXiv:2606.25332v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-…