{
 "license": "CC-BY-4.0",
 "attribution": "Fide AI, Agentic Cyber Explorer",
 "url": "https://agentic-cyber-explorer.pages.dev/events/checkpoint-chatgpt-lockdown-preview-bypass-2026/",
 "asOf": "2026-11-17",
 "id": "checkpoint-chatgpt-lockdown-preview-bypass-2026",
 "date": "2026-11-05",
 "datePrecision": "day",
 "title": "Check Point discloses a patched ChatGPT preview escape affecting Lockdown Mode",
 "lane": "attack",
 "kind": "vulnerability-disclosure",
 "summary": "Check Point Research disclosed a controlled ChatGPT HTML-preview sandbox bypass that could circumvent Lockdown Mode restrictions. Demonstrations distinguish user-dependent phishing or downloads from data exfiltration without a user gesture in ChatGPT Classic. Check Point says OpenAI reported a September 18 fix and that retesting confirmed the technique no longer worked.",
 "whyItMatters": "It shows how a client rendering boundary can undermine a safety setting, while preserving the reported fix and the demonstrations’ interaction requirements.",
 "actors": [
  "check-point",
  "openai"
 ],
 "topics": [
  "sandbox-containment",
  "data-exfiltration",
  "jailbreaks-and-safeguards"
 ],
 "atlas": [],
 "artifacts": [],
 "sources": [
  {
   "url": "https://research.checkpoint.com/2026/chatgpt-lockdown-mode-bypass-phishing-malware-delivery-and-silent-data-exfiltration/",
   "publisher": "Check Point Research",
   "title": "ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration",
   "date": "2026-11-05",
   "type": "primary",
   "accessed": "2026-11-15"
  }
 ],
 "keyFacts": [
  {
   "fact": "The November 5 disclosure concerns a preview-rendering and popup isolation flaw, rather than evidence that the model itself ignored a safety instruction.",
   "locator": "Technical Details"
  },
  {
   "fact": "The phishing and download demonstrations involve user actions. The ChatGPT Classic exfiltration demonstration works without a user gesture under the tested conditions. These are different scenarios.",
   "locator": "Attack surface; Zero-Click Exploitation in ChatGPT Classic"
  },
  {
   "fact": "On September 18, OpenAI told Check Point it had deployed a fix; Check Point reports retesting and confirming that the disclosed technique no longer worked.",
   "locator": "Conclusion"
  },
  {
   "fact": "The source presents researcher demonstrations and responsible disclosure, not an observed in-the-wild campaign.",
   "locator": "Introduction; Conclusion"
  }
 ],
 "significance": 4,
 "fideQuestions": [],
 "methods": [
  "sandbox-escape",
  "sandboxing-egress"
 ],
 "review": "assistant-drafted",
 "addedOn": "2026-11-15",
 "revisions": []
}