Portsuppe

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

TechCrunch Security·4d·Media

Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

Categories cybercrime · regulation · unknown-it-category-16
Original source / advisory
Published
6/6/2026, 8:32:24 PM
Fetched
6/10/2026, 12:19:38 PM
Trust
media · 60/100
Language
en