Risky Bulletin Podcast
April 28, 2025
Risky Bulletin: Top AI models all fall to new prompt injection technique
Presented by

News Editor

Newsreader
A new prompt injection attack is effective against all the big AI models, Poland says Facebook is failing to remove malicious ads, Africa’s largest telco discloses a security breach, and hackers breach Malaysian brokerage accounts.

Brought to you by Dropzone.AI
AI SOC Analysts that never sleep. So you can.