Security
ChatGPT Flaw Let a Planted Prompt Send a Victim's Gmail Data to Another Account
The Hacker News·September 8, 2026·1 min read
Check Point Research demonstrated a ChatGPT vulnerability where a planted prompt in a conversation can silently exfiltrate a user's connected Gmail data to an attacker-controlled ChatGPT account. The attack works while the victim sees the chatbot continuing to answer their questions normally, enabling stealthy data theft from connected services without user knowledge.
Read at The Hacker NewsDaily crypto arcade
Read the news, then play it.
Chainshorts turns crypto headlines into a daily game. Catch up in 60 words, then jump into daily lucky draws for a shot at the pot.