We asked AI agents to fix real security bugs. This is what happened.

1 min read Original article ↗

A field report on what it actually takes to measure whether an AI can fix a vulnerability, and why almost every number you've seen is more flattering than it should be.

Jonathan Santilli

Jonathan Santilli brings over a decade of experience to the field of cybersecurity. Together they're paving the path at Mobb for AppSec.

LinkedIn

Subscribe to our newsletter

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Commit code fixes

in 60 seconds or less.



That’s the Mobb difference

Book a Demo

More interesting articles

Lorem ipsum dolor sit amet consectetur. Augue magna natoque

The State of AI Agent Skill Security — March 2026

Your AI coding assistant is quietly shipping your secrets

AI Code Security: A Modern Playbook for Developers and Security Teams

Auto-Remediation vs AI-Assisted Remediation: Why Automation Matters in Modern DevOps

Subscribe to our newsletter

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.