Threat
ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration - Check Point Research
First reported checkpoint.com
Page published
Earliest dated coverage: 5 Nov 2026 · First observed: 5 Nov 2026 · Latest dated coverage: 5 Nov 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
The ChatGPT Lockdown Mode bypass could expose sensitive conversations without user interaction despite security protections explicitly intended to prevent prompt-injection-driven data leaks.
Check Point Research disclosed a now-patched ChatGPT vulnerability that bypassed Lockdown Mode and could enable silent chat-history exfiltration, credential phishing, and malware delivery. Researchers reported that the exfiltration attack required no user interaction in ChatGPT Classic.