404.Community

Every Microsoft MVP started right where you are now. They answered a question, shared what they learned, or helped someone solve a problem. The award isn’t about being the smartest in the room. It’s about showing up for your community and lifting others as you grow.

In this session, we’ll cover what the MVP award really means, the many ways to contribute, and how nominations actually work. You’ll leave with a simple plan to start building your own story, whether you work in dev, IT, or security.

Come as you are. You don’t need a big following or a long resume. If you care about learning in public and helping others do the same, you already belong here. Let’s grow together.

# Agenda #

• MVP, demystified: what the award actually is (and what it’s not)
• The many roads: speaking, blogging, open source, and everything in between
• Behind the curtain: how nominations and reviews really work
• Finding your lane and getting some momentum going, even from zero
• Keeping the streak alive: staying active and renewing year after year
• Ask us anything: open Q&A, no question too small

# Speakers #

This live online session examines how a single seemingly helpful AI skill can become a serious attack vector, including code modification, secret exfiltration, memory poisoning, and changes to critical workflows, while remaining legitimate in the eyes of the developer.

Participants will see concrete attack paths using a malicious skill lab on GitHub by Elli Shlomo and learn how solutions such as Mitiga’s SkillGate assess skills and configuration files for prompt injection, remote code execution, and data exfiltration techniques, before connecting these findings to runtime defenses across cloud and saas environments.

What you will learn

• How AI agents change the threat model around skills, hooks, and MCP servers
• How a malicious or compromised skill can introduce backdoors, enable secret exfiltration, or poison long‑lived memory
• How to use skillgate to scan public repositories and files before an agent loads them
• How to combine strict pre‑execution review with runtime detection to contain attacks rather than only record them

Who should attend

• Security leaders evaluating AI agents and AI-powered development tools
• Engineering teams deploying agents into production environments
• Security architects designing controls for agent and application security
• Professionals responsible for approving or integrating third‑party AI skills and instruction files into production systems

Speakers