A hands-on session dissecting how AI agents actually fail from a security standpoint, not abstract AI-safety talk, but the specific, well-documented failure modes teams are running into today: prompt injection through tool outputs, excessive agency from over-permissioned tool access, memory/context poisoning, and insecure handling of agent outputs. The first half is a live autopsy of a deliberately compromised demo agent, where attendees trace exactly how it was exploited and what let the attack in. The second half turns adversarial: attendees pair up into red teams and blue teams inside an isolated sandbox, no real systems or data involved, with red teams trying to manipulate the agent into leaking data or calling tools outside its scope, and blue teams patching the vulnerability live. Attendees leave with a working checklist for auditing their own agent stack.

Bengaluru Tech Week 2026 runs September 1-6, 2026 as a decentralized builder week across Bengaluru. BTW is built for founders, engineers, designers, investors, operators, researchers, students, and communities building from Bengaluru for India and the world. Explore the week at bengalurutechweek.com