# A patched ChatGPT HTML preview flaw let crafted content bypass Lockdown Mode restrictions

Published articles for A patched ChatGPT HTML preview flaw let crafted content bypass Lockdown Mode restrictions.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction

DevFeed: [Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction](<https://devfeed.tech/articles/researchers-bypass-chatgpt-lockdown-mode-to-exfiltrate-chats-without-user-interaction-119622.md>)

Original publisher: [Read original article](<https://thehackernews.com/2026/11/researchers-bypass-chatgpt-lockdown.html>)

Author: The Hacker News

Published: 2026-11-05T16:42:32Z

Content type: news

Language: en

Sources: [Cyber Newsroom](<https://devfeed.tech/sources/cyber-newsroom.md>)

Topics: [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [Hacking](<https://devfeed.tech/topics/hacking.md>), [spoofing](<https://devfeed.tech/topics/spoofing.md>), [account takeover](<https://devfeed.tech/topics/account-takeover.md>), [sessions](<https://devfeed.tech/topics/sessions.md>), [Credential theft](<https://devfeed.tech/topics/credential-theft.md>), [credential-based attacks](<https://devfeed.tech/topics/credential-based-attacks.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [a-patched-chatgpt-html-preview-flaw-let-crafted-content-bypass-lockdown-mode-restrictions](<https://devfeed.tech/tags/a-patched-chatgpt-html-preview-flaw-let-crafted-content-bypass-lockdown-mode-restrictions.md>), [account](<https://devfeed.tech/tags/account.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [actor](<https://devfeed.tech/tags/actor.md>), [aes](<https://devfeed.tech/tags/aes.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [details](<https://devfeed.tech/tags/details.md>), [enabling-chat-data-exfiltration](<https://devfeed.tech/tags/enabling-chat-data-exfiltration.md>), [exploited](<https://devfeed.tech/tags/exploited.md>), [introduced](<https://devfeed.tech/tags/introduced.md>), [more](<https://devfeed.tech/tags/more.md>), [openai](<https://devfeed.tech/tags/openai.md>), [openai-chatgpt](<https://devfeed.tech/tags/openai-chatgpt.md>), [patched](<https://devfeed.tech/tags/patched.md>), [this](<https://devfeed.tech/tags/this.md>), [user](<https://devfeed.tech/tags/user.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

A flaw in ChatGPT's HTML preview handling let popup content escape the sandbox and bypass Lockdown Mode, creating a route for silent chat data exfiltration, phishing, or malware delivery. Check Point said nested sandboxed frames allowed a popup to use an unmodified window-opening function; content opened that way no longer faced the same restrictions. An attacker could introduce crafted content through a prompt, malicious GPT, or shared chat. The report says the issue was not limited to the Electron desktop app and that OpenAI patched it on September 18, 2026. The finding illustrates that Lockdown Mode's protections could be undermined by weaknesses in surrounding application features.

### Source excerpt

Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown Mode was introduced by the artif ... Read more Published Date: Nov 05, 2026 (6 hours, 8 minutes ago) Vulnerabilities has been mentioned in this article. CVE-2025-51591