What every business needs to know about prompt injection attacks with Johann Rehberger
Random but MemorableShow Notes
We’re back for a brand-new season! 🎉 And we're kicking things off with an evolving security risk in the AI space: prompt injection attacks. 🤖⚠️
In Watchtower Weekly, we discuss how prompt injection has evolved from chatbot jailbreaks into a serious business risk. As AI tools start reading emails, documents, code, and other sensitive data, we go beyond the headlines to unpack the real-world impact of this attack vector.
To dig deeper, Wade sits down with Johann Rehberger, independent AI security researcher and author of Embrace The Red. Johann explains how malicious instructions can hide inside the content AI tools process, and what organizations can do to reduce the blast radius.
Plus, in #Ask1Password, we explain the purpose of the Developer option in the 1Password desktop app, and how it helps protect SSH keys, environment secrets, and AI-powered development.
More from Random but Memorable
Is your business truly audit-ready, or are you just hoping for the best? 📋🔐
Is shadow AI quietly creating risk inside your business? 🤖🔐 In this episode of Random but Memorable, you’ll learn what happens when employees adopt AI tools faster than teams can track them.
We all know AI models are getting better at finding software vulnerabilities. But can they fix them without creating new problems? In this episode, Wade sits down with Keith Hoodlet, 1Password’s Director of Security Research, to discuss new findings from Off-by-1 Labs.
Always-on access might sound convenient, but it can quietly become a serious security risk. 🔐⚠️ In this bonus episode of Random but Memorable, we’re joined by Rom Carmel, VP of Product Management at 1Password, to introduce 1Password Privileged Access.
Fact or fiction? 🕵️♀️ In this bonus episode, Wade puts Sara and Jayden to the test with a series of cybersecurity myths, urban legends, and viral social media claims.