SecurityThe Hacker Newsabout 7 hours ago
OpenAI Patches ChatGPT Lockdown Mode Flaw
8 min read
OpenAI patched a vulnerability in ChatGPT's Lockdown Mode on September 18, 2026, after researchers found a way to bypass it. The flaw allowed attackers to exfiltrate chat data and deliver malware via nested HTML preview frames, undermining the security barrier introduced in June 2026 to minimize data exfiltration risks.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
