Ep. 18 Kikimora Morozova, AI Security Researcher, Trail of Bits

from Insecure Agents · host Allie Howe

An attacker can hide prompt injections in images that only become to AI systems, enabling data exfiltration on production systems like Google Gemini CLI. Is weaponized image scaling a security vulnerability, or an architectural flaw in how AI systems process multi-modal inputs?

Episode metadata supplied by the publisher feed · Published Dec 22, 2025

Embed this episode

Attribution link and audio player

NOW PLAYING

Ep. 18 Kikimora Morozova, AI Security Researcher, Trail of Bits

0:00 30:43

1×

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

No similar episodes found.

Similar Podcasts

No similar podcasts found.

Frequently Asked Questions

How long is this episode of Insecure Agents?

This episode is 30 minutes long.

When was this Insecure Agents episode published?

This episode was published on December 22, 2025.

Can I download this Insecure Agents episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.

URL copied to clipboard!