Agents in the Wild - An Invite-Only Morning Briefing for NYC Security Leaders
Agents are now writing code, touching production, and calling tools across every team that matters: Claude, Cursor, Cowork, and the rest. We've spent the last year inside these environments, and the agentic layer doesn't behave the way the threat models assume.
This is a closed-door session on what we're actually seeing: sandbox escapes across the agents people are deploying right now, the first cases of one agent compromising another in a shared environment, and the runaway token and tool-call patterns that turn out to be the earliest signal something's wrong.
No slides full of frameworks. Field findings from Tenet's security research team.
Schedule:
08:00-08:30 | Arrival & Breakfast
08:30-09:30 | Breaking & Attacking the agentic layer: from visibility gaps to sandbox escapes to other emerging attacker techniques
09:30-10:00 | Networking & Discussion
Session Agenda:
Sandbox escape techniques across Claude and Claude Cowork
Agent-on-agent: lateral movement inside the agentic layer
Common Agentic misbehaviors
Where the visibility gaps are, and what's worth watching
About Barak Sternberg (Speaker):
Barak Sternberg is a cybersecurity researcher, offensive security specialist, and a returning DEFCON speaker. His research career spans over 15 years across every major attack surface of the last decade: from IoT to browser extension exploits (DEFCON 29), to Kube infra attacks (with Nevo), to smart device hacking (DEFCON Safe Mode IoT Village). He's presented at DEFCON (twice), Hacktivity, RootCon, BSides, Intent, and numerous other security conferences worldwide. He's a Unit 8200 veteran and Israel Defense Prize recipient. His research has consistently focused on finding novel attack chains in emerging technology before attackers do, across years in offensive cybersecurity. He also co-founded Wild Pointer (offensive security, Fortune 500 clients) and more recently co-founded Tenet Security as CEO with Nevo Poran: but the research came first, the company came from the research, not the other way around. He leads Tenet while staying hands-on - the exploit chains in this talk came directly from his team's research