Researchers hack OpenAI by exploiting vulnerabilities in Claude

Security researchers used Claude to hack OpenAI's systems.

Published 2h4 sources✓ ConfirmedMajorupdated 59m

≈ 14sSpeed

The fact

They took over employee accounts and accessed an internal code repository.

The vulnerabilities were reported after being successfully exploited.

4 sources — click a link to read an article on the topic:

Explore this topic

Auto-synthesis from 4 media sources · identified on September 18, 2026