'AI security controls are only as strong as the wider application environment around them': OpenAI forced to patch after experts bypass ChatGPT 'lockdown mode' to gain access to entire chat history

T2Covered by 1 source · first reported by TechRadar / Tom's Guide / PCWorld / Pocket-lint / Stuff at 06 Nov, 16:05 UTC

Lockdown Mode was bypassed with HTML popups but OpenAI now fixed it.

aiconsumer

Sources

• T2'AI security controls are only as strong as the wider application environment around them': OpenAI forced to patch after experts bypass ChatGPT 'lockdown mode' to gain access to entire chat historyTechRadar / Tom's Guide / PCWorld / Pocket-lint / Stuff06 Nov, 16:05