OpenAI introduces Lockdown Mode to enhance data security against prompt injection attacks

Jun 6, 2026

AI Summary

OpenAI has launched Lockdown Mode, a feature aimed at protecting sensitive data from prompt injection attacks. This mode disables live web browsing and certain content retrieval functions, although the company acknowledges that vulnerabilities may still exist.

OpenAI has introduced Lockdown Mode to provide additional protection against prompt injection attacks, which involve embedding malicious instructions in content sources.
The feature disables live web browsing, retrieval of web images, deep research, and agent mode, allowing only access to cached content.
Despite these measures, OpenAI warns that ChatGPT may still be susceptible to prompt injections from cached web content or uploaded files.
Lockdown Mode is specifically designed for individuals and organizations that manage sensitive data and seek enhanced protection against data exfiltration risks.
The rollout of Lockdown Mode is currently underway for self-serve ChatGPT Business accounts and eligible personal accounts.

openaidata protectionprompt injectionchatgptsecurity

OpenAI introduces Lockdown Mode to enhance data security against prompt injection attacks

Related Stories

OpenAI Launches Bio Bounty Program for GPT-5.5

Google's SynthID Successfully Identifies Fake Image of Senator McConnell

AI's Impact on Jobs Sparks Calls for Educational Reform Similar to Early 20th Century Changes

AI Tools Vulnerable to Prompt Injection Attacks for Botnet Creation