I Brought an AI to a Hacking Contest (and Won)(medium.com)
medium.com
I Brought an AI to a Hacking Contest (and Won)
https://medium.com/@pol.avec/i-brought-an-ai-to-a-hacking-contest-and-won-a8c9998745c9
8 comments
For those that don't know, Pi is the minimal agent harness powering Open Claw too
https://github.com/badlogic/pi-mono
https://github.com/badlogic/pi-mono
I stopped reading at "The competition itself was a beginner-friendly offensive security CTF..."
Beating a bunch of inexperienced people does not impress me, and is poor sportsmanship as well.
why would a beginner like me participating in a beginner-friendly competition be poor sportsmanship?
I imagine the competition wasn't about who could use ai tools the best, but who knows...
The competition was about solving the challenge, and was aimed at novices like me, so your point is moot and out of place. Even organizers said out loud they encouraged AI tools and checked on each team (me included) often.
The most interesting part for me was reviewing the full conversation logs afterward to figure out whether my steering actually helped or hurt. Turns out about 4 of my 24 interventions were counterproductive and the agent solved the last two phases completely on its own.
The repo has the full writeup, all the exploit scripts, and a table rating every single human message I sent: https://github.com/kafkasl/ctf
Happy to answer questions about the process, the agent, or the competition.