-
Security incident 8 Nov 2026· 10:35 UTC Original report: 6 Nov 2026
Researchers bypass ChatGPT Lockdown Mode; OpenAI patched the flaw
Check Point Research found a way around ChatGPT's Lockdown Mode that could let chat data leave the app without user interaction. OpenAI fixed it after responsible disclosure.
-
Security incident 8 Nov 2026· 04:09 UTC Original report: 4 Nov 2026
KeyHunter operation harvested 2,233 LLM API keys
SOCRadar reports a threat actor that harvested 2,233 API keys from Anthropic, OpenAI, Google and DeepSeek, mostly from misconfigured cloud infrastructure.
-
Security incident 8 Nov 2026· 00:09 UTC Original report: 2 Nov 2026
LLMjacking: stolen LLM access is running up six-figure daily bills
Google Threat Intelligence Group and Mandiant report stolen LLM access used to run up fraudulent API bills of more than $100,000 a day at some victims.