OpenAI debuts ChatGPT Lockdown Mode to block prompt injection attacks

OpenAI has introduced Lockdown Mode, a new security feature for ChatGPT designed to reduce prompt injection attack risks for users handling sensitive data. The mode disables live web browsing, web image retrieval, deep research, and agent mode to limit potential attack vectors. While OpenAI acknowledges it cannot eliminate all prompt injection risks—since cached content and uploaded files remain vulnerable—the feature aims to lower the likelihood of sensitive data exfiltration. It is currently rolling out to ChatGPT Business accounts and eligible personal accounts.