OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

OpenAI announced a new feature called Lockdown Mode on June 6, 2026. The feature is designed to provide additional protection from prompt injection attacks by disabling live web browsing and deep research within ChatGPT.

According to OpenAI, Lockdown Mode is intended to help enterprise customers protect sensitive data. However, the company noted that even with Lockdown Mode enabled, ChatGPT could still be vulnerable to prompt injections from cached content or uploaded files. This limitation means the feature does not provide complete protection.

The announcement highlights ongoing security concerns around large language models. Prompt injection attacks remain a challenge for AI companies, as models can be manipulated to reveal sensitive information or bypass safety measures. OpenAI's Lockdown Mode represents one approach to mitigating these risks, though it does not fully resolve the underlying vulnerability.