OpenAI Launches Lockdown Mode Against Prompt Injection

OpenAI has introduced Lockdown Mode, a new ChatGPT feature designed to protect sensitive data from prompt injection attacks, where malicious instructions are hidden in webpages or other content. The mode disables live web browsing, image retrieval, deep research, and agent mode. OpenAI acknowledges the feature does not fully eliminate prompt injection risks, as threats can still appear in cached content or uploaded files. Lockdown Mode is aimed at organizations and individuals handling sensitive data and is currently rolling out to self-serve ChatGPT Business accounts and eligible personal accounts.