←── back to feed
/topics/openai-hacked-via-claude-in-security-breach

OpenAI hacked via Claude in security breach

7 items3 sourcesupdated 1d agotrend 0

A team of three independent security researchers at Hacktron used Anthropic's Claude Opus 4.8 and 5 to breach OpenAI's systems in under 72 hours, gaining access to employee accounts and OpenAI's GitHub repository called Monorepo. The researchers demonstrated the vulnerability by sending a pull request from a compromised employee Codex account before responsibly disclosing the flaws.

  • Three researchers at Hacktron exploited vulnerabilities using Claude Opus 4.8 and 5 models
  • Breach took less than 72 hours to compromise OpenAI employee accounts
  • Attackers accessed OpenAI's Monorepo GitHub repository containing algorithmic secrets
  • Researchers proved access by submitting pull request from employee's Codex account
  • Vulnerability was discovered through Discourse before responsible disclosure