Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

Originally restricted to enterprise executives and security teams, OpenAI is now expanding its Lockdown Mode to all ChatGPT users worldwide.

OpenAI has launched Lockdown Mode, an optional feature aimed at safeguarding users from prompt injection attacks, a growing threat targeting conversational AI systems.