Can a local AI pentesting agent produce findings I can independently reproduce?
An overnight Strix experiment with local models, a vulnerable web app, and a pentest report that yields results.
THE ARCHIVE
Transmissions from the lab.
Study notes say what is still theoretical. Field logs document the method. Investigations make evidence explicit.
01
BUILDING THE DVNLL LAB 002 · build log
02BUILDING THE DVNLL LAB 001 · build log
03I Left an AI Security Agent Running Overnight. Then I Read the Report.
An overnight Strix experiment with local models, a vulnerable web app, and a pentest report that didn’t match the target.
AI RED TEAMING NOTE 001 · study note
Building an AI For a Spam Classifier (With Python)
A study note on how to implement a spam classifier with AI from scratch using python.