Two bugs let hackers hijack OpenAI employee accounts in 72 hours, reaching monorepo

JeffLadish · x · 2026-09-18

Security researcher S1r1u5 claims that on July 25 two bugs allowed taking over ChatGPT/Codex accounts of OpenAI employees and some unrelated users, reaching connected services like Outlook, Slack and GitHub — proven by opening a PR in OpenAI's internal codebase, all in under 72 hours.

Jeff Ladish points out the bigger implication: full monorepo access means the attackers could potentially have downloaded OpenAI's entire codebase. The claim is researcher-reported; OpenAI has not yet responded officially.

Related event: Researchers Used Claude to Breach OpenAI's Internal Codebase(22 posts)→

Original post →

More from Companies & People

Companies & People channel →