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. Among other things, Lockdown Mode will disable live web browsing (so you can only access cached content), the retrieval and display of images from the web (you can still generate images), deep research, and agent mode.
When Lockdown Mode is active, ChatGPT will only access saved web content and won't show images from the internet, making your conversations more secure.
This mode also turns off deep research and agent features to further prevent unwanted data access.
Original reportingOpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks | TechCrunchRead original ↗