Researchers Use Claude Opus 5 to Exploit OpenAI Vulnerabilities and Access Internal Systems

Three researchers at security firm Hacktron used Anthropic's Claude Opus 5 to chain two vulnerabilities and successfully take over ChatGPT and Codex accounts belonging to several OpenAI employees. The attack chain exploited a bug in OpenAI's public help forum software and a weakness in OpenAI's login system, ultimately allowing the researchers to access an internal OpenAI code repository. This activity was conducted as security research.