Developing story · 2 episodes · 13 Sept to 19 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.
-
Hacktron uses Claude Opus 5 to breach OpenAI staff accounts via chained flaws
Three researchers at the security firm Hacktron employed Anthropic's Claude Opus 5 to combine two vulnerabilities and gain access to OpenAI staff accounts for ChatGPT and Codex. The chain started…
1 source -
Researchers used Claude Opus 5 to compromise OpenAI employee accounts, report says
Security researchers from Hacktron compromised multiple OpenAI employee accounts on July 25, 2026, by chaining two critical vulnerabilities in less than 72 hours. The team, led by Harsh Jaiswal,…
1 source
Who and what