OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
TechCrunch AI Anthony Ha June 6, 2026

AI Summary— plain English for professionals
# OpenAI Adds New Safety Feature to ChatGPT OpenAI has introduced a new protection called Lockdown Mode designed to keep your sensitive information safer when using ChatGPT. While the feature won't completely eliminate all security risks, it makes it significantly harder for someone to trick the AI into accidentally revealing private data. Think of it as a guardrail that limits what ChatGPT will share, even if someone tries to manipulate it into doing so.
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.
More from Latest News
Get new guides every week
Real AI income strategies, tool reviews, and plain-English news — free in your inbox.
or enter email


