# Anthropic’s Claude helped researchers breach OpenAI in under 72 hours

https://mins.news/en/item/65060

- CryptoSlate, 2026-09-19 00:40 UTC
- Tech
- Original: https://cryptoslate.com/anthropics-claude-helped-3-researchers-breach-openai-in-under-72-hours/

> Cybersecurity startup Hacktron says three researchers used Anthropic’s Claude to chain vulnerabilities in OpenAI’s image processing and identity infrastructure, reaching several employees’ ChatGPT and Codex accounts and an internal repository in under 72 hours. They said they did not inspect proprietary source code. OpenAI fixed the identity flaw and paid a $6,500 bounty.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [Researchers used Claude to breach OpenAI’s internal systems](https://mins.news/en/item/65146) — CGTN, 2026-09-19
- [Security researchers used Claude to help hack into OpenAI](https://mins.news/en/item/64492) — The Verge, 2026-09-18
- [Report: Researchers breached OpenAI with Claude](https://mins.news/en/video/64318) — ABC News, 2026-09-18