threat-intel
Researchers used Claude to hack OpenAI employees' ChatGPT accounts
High
Summary
Researchers successfully exploited a vulnerability in the Claude AI model to gain unauthorized access to ChatGPT accounts belonging to OpenAI employees. This highlights a growing concern about the security of AI models and the potential for misuse when they are used to impersonate legitimate users.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data