AnalysisCybersecuritySeptember 8, 2026

ChatGPT flaw lets planted prompt exfiltrate Gmail data

Check Point Research demonstrated a single planted instruction could make ChatGPT read a user's Gmail data and send it to another ChatGPT account via a hidden channel, without the user's knowledge. The attack required the instruction to be in the conversation beforehand, via a pasted prompt, shared chat, or custom GPT.

1 source

More stories today

Open the live feed