Put your AI coding assistants to the test in a real-world web application security sandbox.

In this hands-on workshop, participants will use tools such as GitHub Copilot or VS Code alongside an OWASP Juice Shop instance to safely identify and patch common security flaws (such as injection and broken access control). You will practice a rigorous, human-in-the-loop developer workflow: isolating a vulnerability, creating a branch, prompting the AI for a secure fix, verifying the patch against insecure defaults, and writing clean PR documentation. Learn how to critique AI-generated code, spot dangerous hallucinations, and maintain strict human oversight.

This workshop is part of a series offered by the AI Collaborative Programming group, a cross-unit partnership between the Hesburgh Libraries, ND Learning, and the Office of Information Technology.

Presenter:

Rob Wieck — Senior Research Software Engineer / Product Owner, AI Enablement