Copilot Studio Agents: Attacks and Defenses

About the session

Copilot Studio enables no‑code AI agents built on top of the Microsoft Power Platform allowing teams to automate workflows and operate inside enterprise environments using real permissions, creating a broad and often misunderstood attack surface.

In this session, we’ll cover how Copilot Studio agents are built, where common attack paths emerge, and how organizations can defend against agent‑driven risk. You’ll see both offensive and defensive perspectives, with practical guidance teams can apply today.

You’ll learn:

Where Copilot Studio agents inherit access and risk
Common attack paths and how they’re exploited
Practical controls to secure agents and reduce exposure

Walk away with a clear understanding of how to build, test, and defend Copilot Studio agents before they become a blind spot in your environment.

Meet the Speaker

Simon Maxwell-Stewart

Staff Security Researcher

Simon Maxwell-Stewart is a University of Oxford physics graduate with over a decade of experience in the big data environment. Before joining BeyondTrust, he worked as a Lead Data Scientist in healthcare, and successfully brought multiple machine learning projects into production. Now working as a "resident graph nerd" on BeyondTrust's security research team, Simon applies his expertise in graph analysis to help drive identity security innovation.