Uploaded January 2026 | Updated September 2026, 2 weeks ago

---

In this clip from Today in Tech, security researcher Michael Bargury (from Zenity) explains how ChatGPT connectors can be abused to silently manipulate responses, inject malicious code, and turn your AI assistant into a long-term surveillance tool. This is not theoretical. It's already possible.

#todayintech

Follow TECH(talk) for the latest tech news and discussion!

------------------------------­----

Keith Shaw
linkedin.com/in/shawkeith

SUBSCRIBE: youtube.com/@CWTECHtalk

TIKTOK: tiktok.com/@todayintechpodcast