My AI pentest agent reported 23 root shells. It had actually popped zero.

I've been building an autonomous penetration-testing agent — an LLM driving real

tools (nmap, masscan, hydra, Metasploit, searchsploit) around a loop: recon a

target, pick an exploit, fire it, decide whether it worked, move on. Everything

below runs against a deliberately vulnerable Metasploitable VM in an isolated

lab. Nothing here is a technique for attacking systems you don't own; it's a