A public AI security challenge saw 2,000 people attempt to leak secrets via prompt injection, with all 6,000 attempts failing, reflecting progress in frontier model defenses but also revealing lingering risks.
Lockdown Mode uses deterministic rules to block outbound requests, cutting off the data exfiltration vector in prompt injection attacks and implicitly revealing the weakness of default ChatGPT security.
A real-world attack where hackers bypassed Instagram's account recovery by simply asking Meta's AI chatbot to link a new email, revealing the severe risks of wiring AI directly into critical systems without proper authorization boundaries.
A critical security flaw in Microsoft Copilot Cowork allowed attackers to exfiltrate user files via prompt injection by exploiting auto-sent emails and pre-authenticated download links.