Talk

Prompt Attack Threat Landscape in action

March 19, 10:30 (SIDE-EVENT (2A))

This workshop goes beyond classic prompt injection and explores the broader threat landscape of prompt attacks in modern AI systems. We break down real-world agent architectures and examine how prompt attacks propagate through tools, memory, retrieval systems, and external integrations. Attendees will additionally have the option to work in an agent lab environment to actively exploit the systems discussed, observing how attacks move across components and trigger unintended behavior. The goal is to build a realistic understanding of how prompt attacks affect production-grade AI systems.

To register to this workshop, you can click here

Entrance to this side event is permitted only with a valid ticket to Insomni’hack 2026!

Speaker

Elliot Ward

Elliot is a Staff Security Researcher on Check Point's Agentic Security team. His career spans the full spectrum of application security: years as a consultant delivering penetration tests, code reviews, and threat models; building and leading an AppSec program internally within a Swiss bank; and conducting vulnerability research at Snyk. He now brings this end-to-end offensive and defensive expertise to the emerging frontier of AI agent security.

Organized by

Technology partners

Partner events

Scroll to Top