New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

Summary

OpenAI has introduced a new Lockdown Mode for ChatGPT to combat data exfiltration stemming from prompt injection attacks. This optional security setting limits features like live web browsing, image support, and file downloads that could be exploited to send sensitive data to external infrastructure. While it significantly reduces the risk, OpenAI cautions that it does not guarantee complete prevention of data exfiltration or all prompt injection effects.

Full text

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration Ravie LakshmananJun 06, 2026Cybersecurity / Artificial Intelligence OpenAI has begun rolling out a new Lockdown Mode to ChatGPT for eligible personal accounts to reduce the risk of data exfiltration arising from prompt injection attacks. The feature is primarily designed for people and organizations that handle sensitive data and require stricter protection guarantees. Lockdown Mode is available to logged-in users across Free, Go, Plus, and Pro, and self-serve ChatGPT Business plans. "Lockdown Mode is an optional advanced security setting that limits many tools and capabilities in OpenAI products that can connect to the web or external services," OpenAI said. "It is designed to reduce the risk of data exfiltration from prompt injection attacks by limiting outbound network requests, at the expense of disabling or limiting some useful features." The safeguards are aimed at hardening the attack surface against prompt injections, which continues to be a "frontier" problem impacting all large language models (LLMs). Specifically, they build upon sandboxing and existing controls to combat URL-based data exfiltration mechanisms to limit outbound network requests that could potentially transmit sensitive data to attacker-controlled infrastructure. The idea is not to stop prompt injections from occurring. Nor does it change the way memory or file uploads work, or the ability to share a conversation. Rather, the goal is to eliminate potential pathways through which the data could be exfiltrated. To that end, Lockdown Mode disables the following features - Live web browsing, which is limited to accessing only cached content Image support, for displaying images in regular responses or retrieving images from the web Deep research Agent mode Canvas networking, which prevents users from approving Canvas-generated code to access the network File downloads, which block downloading files for data analysis Pointing out the feature is not "intended for everyone," OpenAI also noted that both Lockdown Mode and Developer Mode cannot be used at the same time, adding that turning on one disables the other. "Lockdown Mode is designed to substantially reduce the risk of prompt injection-based data exfiltration in ChatGPT and supported OpenAI products, but it does not guarantee that data exfiltration cannot happen," the company said. "Risk may remain through enabled Apps, unforeseen combinations of capabilities, or newly discovered techniques." "Lockdown Mode also does not prevent all other effects of prompt injection attacks. For example, a malicious instruction hidden in an uploaded file could still affect ChatGPT's behavior, and cause an incorrect answer." The development comes as OpenAI has also launched a new account management feature that enables users to review active ChatGPT sessions and log out of individual or all sessions if signs of unauthorized account activity are detected. The listed sessions include information about the device, the app used, approximate location, sign-in date and time, whether the device is trusted, and whether it's the current session. Found this article interesting? Follow us on Google News, Twitter and LinkedIn to read more exclusive content we post. SHARE     Tweet Share Share Share SHARE  Account security, artificial intelligence, ChatGPT, cybersecurity, data exfiltration, Large language model, OpenAI, Prompt Injection, sandbox, Web Browsing ⚡ Top Stories This Week Google June 2026 Android Update Patches 124 Flaws, One Actively Exploited Oracle WebLogic CVE-2024-21182 Added to KEV Catalog After Active Exploitation Dashlane Discloses Brute-Force Attack, Encrypted Vaults of Fewer Than 20 Users Downloaded Miasma Supply Chain Attack Compromises Red Hat npm Packages with Credential-Stealing Worm ⚡ Weekly Recap: New Linux Flaw, PAN-OS Exploit, AI-Powered Attacks, OAuth Phishing and More OpenAI Codex Authentication Tokens Stolen in codexui-android npm Supply Chain Attack PAN-OS GlobalProtect Authentication Bypass (CVE-2026-0257) Under Active Exploitation ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface Attackers Use LLM Agent for Post-Exploitation After Marimo CVE-2026-39987 Exploit Threat Actors Exploit Critical FortiClient EMS Flaw to Deploy Credential Stealer Microsoft Slams Public Zero-Day Disclosures Amid GitHub Researcher Account Removal ThreatsDay Bulletin: Claude Security Plugin, Azure Priv-Esc, Kali365 MFA Bypass, FIFA Scams +15 More Malicious npm Package Stole Files From Claude AI User Directory via GitHub GlassWorm Malware Takedown Disrupts Developer Supply Chain Attack Infrastructure AI Chatbot Recommendations Redirect Users to Cryptojacking Malware Sites Microsoft Patches SharePoint RCE Flaw CVE-2026-45659 Across Server Versions ⭐ Featured Resources Your Employees Are Using AI in Ways You Can’t See – 2026 State of AI Report Learn How to Stop Attacks Before They Reach Your EDR – With PHASR Watch AI Turn Vulnerabilities Into Working Exploits in Minutes (See the Demo) [Guide] The Real Security Risks of Shadow AI (And Where You’re Exposed)

Entities