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.
In Brief
Posted:
1:32 PM PDT · June 6, 2026
Image Credits:sarayut Thaneerat / Getty Images
OpenAI announced a new feature that it says will provide additional protection from prompt injection attacks, where malicious chatbot instructions are hidden in webpages and other content sources.
OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks
OpenAI's new feature protects you from prompt injection attacks
ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection
OpenAI Announces Unnerving New ChatGPT Feature Named 'Lockdown Mode'
New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration
OpenAI rolls out Lockdown Mode for users handling sensitive information - The Economic Times
How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)
OpenAI's new ChatGPT Lockdown Mode takes aim at one of AI's biggest security challenges
OpenAI is now rolling out Lockdown Mode to more ChatGPT users
OpenAI Rolling Out ChatGPT Account Security Controls
ChatGPT's new Lockdown Mode disables live browsing, agent mode, and deep research to stop attackers from stealing data through…
OpenAI has launched Lockdown Mode, an optional feature aimed at safeguarding users from prompt injection attacks, a growing…
OpenAI's new Lockdown Mode for ChatGPT disables web access, Deep Research, and Agent Mode to make data theft through prompt…
"Lockdown Mode is not intended for everyone," OpenAI's blog post says. In other words, you're probably not important enough.
OpenAI Lockdown Mode limits outbound ChatGPT requests to reduce prompt injection data exfiltration risk for eligible accounts.
OpenAI has launched Lockdown Mode to combat prompt injection attacks, a security feature designed for users handling sensitive…
