OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot
TL;DR
US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’ Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of security issues at the company. A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more. Continue reading...
Nauti's Take
For AI teams, this is a practical identity-security test: employee accounts, local caches, and active sessions need separate controls and reliable revocation. First verify what an exposed ChatGPT account can reach through browser sessions, tokens, or synced files before enabling broader agent capabilities.
Sources