OpenAI announced Lockdown Mode in June 2026, a new ChatGPT feature designed to reduce the risk of sensitive data being exposed through prompt injection attacks — a technique where malicious instructions are hidden inside webpages or other content sources.
When enabled, Lockdown Mode disables several ChatGPT capabilities, including live web browsing, retrieval and display of images from the web, deep research, and agent mode. Users retain access to cached web content and can still generate images.
OpenAI acknowledged that the feature does not eliminate the threat entirely. The company stated that even with Lockdown Mode active, ChatGPT “could still be vulnerable to prompt injections,” which “could appear in cached web content or in an uploaded file, and could still affect the behavior or accuracy of a response.” The stated goal is to reduce the likelihood that sensitive data is shared during such an attack, not to prevent injections outright.
OpenAI was explicit about the feature’s intended audience. “Lockdown Mode is not intended for everyone,” the company said. “It is designed for people and organizations that handle sensitive data and want stricter protection from data exfiltration risks related to prompt injection.”
The rollout is currently underway for self-serve ChatGPT Business accounts and eligible personal accounts.
For organizations that regularly work with confidential information, the feature may offer a meaningful layer of control — though OpenAI’s own caveat that vulnerabilities remain suggests users should treat it as one safeguard among several rather than a complete solution.
Source: TechCrunch