*NEW* Mini Box - When AI Follows the Wrong Instructions
Welcome to your Mini Box: When AI Follows the Wrong Instructions. As AI tools become part of everyday work, recognizing and understanding prompt injection is a critical security habit to build right now. This Mini Box introduces the technique where attackers embed hidden instructions inside ordinary documents, web pages, and emails, counting on an AI tool to read them and act on them.
In this topical mini box, you’ll find:
- A one-pager that walks employees through what prompt injection is, why it matters right now, and what they can do about it today. We have provided a subject line for email distribution, but feel free to share via intranet, blog, or whatever channel works best for your organization.
- A chat message using a quick interactive scenario to reinforce one simple habit: think before you let your AI tools loose on outside content. Depending on your messaging client, you may need to save the provided GIFs to your computer and attach them to your
chat messages.
You are absolutely free to edit and customize the content we send. Make this Mini Box your own! Please don’t hesitate to let us know if there’s something you would like to see in the future.
