Hard Fork AI cover image

OpenAI Sounds Alarm: Perpetual Agent Prompt Plague

Hard Fork AI

00:00

What prompt injection looks like

Jaeden describes examples of malicious instructions hidden in emails or webpages that manipulate agents to take harmful actions.

Play episode from 02:03
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