Researchers used Claude to hack OpenAI employee accounts in under 72 hours
The Verge AI · rss · 2026-09-18
Three independent security researchers at Hacktron say they used Anthropic's Claude Opus 4.8 and 5 to help them compromise OpenAI employee accounts in under 72 hours, gaining access to OpenAI's GitHub repository "Monorepo," which reportedly contains OpenAI's algorithmic secrets, the Wall Street Journal reports.
The entry point was Discourse, the third-party service hosting OpenAI's community forum. The team stopped short of reading Monorepo's internal code but sent a pull request from an employee's Codex account to prove access. The episode highlights how AI-assisted attacks can dramatically compress the time needed to breach frontier AI labs.
More from Safety
- North Korea stole $6.3B from Binance via fake job interview that compromised engineers — aakashgupta · 2026-11-04
- OffsecCyber dataset combines HackerOne reports and CVEs to train pentesting LLMs — AccBalanced · 2026-11-04
- Abliterated GLM-5.3 pulls off red-team exploit in 3:41 for $0.02, stock model refuses — bratton · 2026-11-04
- AI industry bet on both parties: $55M+ spent this election cycle via dual PACs — ChrisGPT · 2026-11-04
- Valid tokens, allowed actions, zero intent checks: the agent security gap nobody solves — Cytersmyz · 2026-11-04
- Princeton paper: harsher penalties can make AI auditors inspect less — Few-Decision6287 · 2026-11-04