Agentic AI is being deployed. Governance frameworks exist. The hands-on controls don't. This workshop closes the gap - participants operate a live enterprise agent, attack it across five of the OWASP Top 10 Agentic AI vulnerabilities - goal hijacking, tool misuse, memory poisoning, privilege abuse, and human trust exploitation - then retrofit real governance controls and apply those that hold. Every participant leaves with an agent hardening checklist, a governance policy template, and a red team prompt kit to test their own systems.

* Please note: This is not included in the Main Conference registration and requires a separate registration.