DCSG1 – Autonomous and Exploitable: Breaking AI Agents before they break everything else – Aaron Ang

The hottest thing in AI right now is agentic systems — LLMs that browse the web, write and execute code, manage your email, call your APIs. They’re being deployed faster than anyone understands the attack surface. Join Aaron as he presents a systematic teardown of AI agent security: how agents inherit trust they shouldn’t have, how a single adversarial webpage can hijack a browsing agent mid-task, and how multi-agent pipelines create exploit chains that no single guardrail can stop.

Aaron will demonstrate end-to-end agent compromise scenarios — from initial prompt injection through a poisoned tool response, to achieving persistent influence over agent memory and downstream actions. Live. On real frameworks.

This isn’t theoretical. These systems are in production. Let’s talk about what that means for all of us.DEFCONConferenceRead More