Episode 433
Your AI reads the small print, and that's a problem. This week in episode 433 of "Smashing Security" we dig into LegalPwn - malicious instructions tucked into code comments and disclaimers that sweet-talks AI into rubber-stamping dangerous payloads (or even pretending they’re a harmless calculator).
Meanwhile, new research from Anthropic reveals that hackers have already used AI agents to break into networks, steal passwords, sift through stolen data, and even write custom ransom notes. In other words, one hacker with an AI helper can work like an entire team of cybercriminals.
Plus: a joyous geek detour into keyboard history, and the most diabolically annoying, fully functional AI-generated CAPTCHA that you will love to inflict on your friends.
EPISODE LINKS:
SPONSORED BY:
SUPPORT THE SHOW:
Tell your friends and colleagues about “Smashing Security”, and leave us a review on Apple Podcasts or Podchaser.
Become a supporter via Patreon or Apple Podcasts for ad-free episodes on our early-release feed!
FOLLOW THE SHOW:
Follow us on Blue
Published on 1 week ago
If you like Podbriefly.com, please consider donating to support the ongoing development.
Donate