Developing story · 2 episodes · 19 Sept to 22 Sept
Claude Opus 5 Account Breach Saga
A series of attacks using Claude Opus 5 targeted OpenAI employee accounts, revealing chained security flaws. The latest episode confirms the breach and has spurred urgent security reviews across the organization.
-
Three researchers used Claude to breach OpenAI's code repository in 72 hours, report says
Security researchers from Hacktron reportedly used Anthropic's Claude to infiltrate OpenAI's code repository in less than 72 hours, according to the Wall Street Journal and TechCrunch. The breach…
1 source -
Hacktron researchers used Claude Opus 5 to breach OpenAI staff accounts via chained flaws
Three researchers from security firm Hacktron used Anthropic's Claude Opus 5 to chain two flaws — a libheif image parsing bug in OpenAI's public Discourse forum and a shared SSO login weakness — to…
3 sources
Who and what