🤖 AI Published 20d ago · 2 sources

Researchers Use Anthropic's Claude to Hack OpenAI Systems

💡 Why it matters

This incident underscores the urgent need for robust AI security protocols as tools become weapons in corporate espionage.

Security researchers exploited vulnerabilities in OpenAI's systems using Anthropic's Claude, taking over employee accounts and accessing an internal code repository before reporting the flaws. The attack demonstrated cross-company AI tool exploitation.