OpenAI has started rolling out Lockdown Mode for personal ChatGPT accounts, enhancing security against prompt injection attacks. Initially introduced for enterprise users in February, this feature is now accessible to Free, Go, Plus, Pro, and self-serve Business users via the Settings menu under Safety and security. Prompt injection involves attackers embedding malicious instructions in content that AI may process, and Lockdown Mode serves as a protective measure rather than a complete solution. It restricts functionalities such as live web browsing to cached content, disables Deep Research and Agent Mode, blocks file downloads, and prevents the display of web images in responses, although users can still generate images and upload files manually. Additionally, OpenAI is introducing an active session manager that allows users to view and log out of devices accessing their accounts. This security feature is particularly beneficial for executives and security teams managing sensitive conversations, as Lockdown Mode is not intended for all users.