PrivacyHigh
Hacking OpenAI
- Occurred
- Sep 29, 2026
- Published
- Sep 29, 2026
- Source
- AI Incident Database
Summary
On July 25, 2026, we chained two critical vulnerabilities to compromise multiple OpenAI employees’ ChatGPT accounts. With these accounts, we could then access internal OpenAI repositories, and potentially many other connectors. To prove we ... (report_number: 8007)
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Unauthorized access to employee accounts and internal repositories constitutes a significant data breach and privacy violation.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8