The Rollup cover image

George Zeng on Why Your AI Agent Isn't Safe

The Rollup

00:00

Prompt injection and agent-to-agent threats

George details architectural prompt-injection defenses and encrypted secrets to prevent malicious agent interactions.

Play episode from 07:48
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app