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…