Researchers at security firm Hacktron used Anthropic's Claude Opus 5 to chain a vulnerability in OpenAI's public help forum software with a weakness in OpenAI's login system, taking over several OpenAI staff members' ChatGPT and Codex accounts and reaching an internal OpenAI code repository as part of authorized security research.
Disclosed 19 September 2026 · Record updated 19 September 2026
Researchers gained account takeover of several OpenAI employees' ChatGPT and Codex accounts and accessed an internal OpenAI code repository, though this was conducted as authorized security research.
IncidentsResearchers at Hacktron chained a help-forum bug with a login weakness to reach OpenAI employee accounts and an internal code repository, in authorised security research.
19 Sept 2026
