OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks (opens in new tab)  🪄Prompt Engineering  Content type: News

OpenAI has begun rolling out Lockdown Mode to ChatGPT, a new security setting designed to block attackers from stealing data through prompt injection attacks. The feature disables live web browsing, agent mode, deep research, image retrieval, Canvas networking, and file downloads. It is available to logged-in users across Free, Go, Plus, Pro, and self-serve ChatGPT […] at The Next Web