Between 18–20 September 2026, security researchers at Hacktron AI reported using Anthropic's Claude Opus 5 to exploit vulnerabilities in OpenAI's systems. The team took over ChatGPT and Codex accounts belonging to OpenAI staff and accessed an internal code repository in under 72 hours.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
Researchers used Claude to reach an OpenAI employee account and sensitive GitHub data.
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.
this outlet adds: especially, since, turning, filled, hate, really, watch, dummies
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws. https:// techcrunch.com/2026/09/18/rese archers-used-anthropics-claude-to-hack-into-openai/?utm_source=dlvr.it&utm_medium=mastodon
A team of three independent security researchers at Hacktron says it took less than 72 hours for them to hack into OpenAI employee accounts using Anthropic's Claude Opus 4.8 and 5, the Wall Street Journal reports. They were able to access OpenAI's GitHub repository, called "Monorepo," which reportedly contains "OpenAI's algorithmic secrets," according to the […]
Agentic exploits for the win (again)
Researchers used Claude to hack OpenAI https:// arstechnica.com/ai/2026/09/res earchers-used-claude-to-hack-openai/
Researchers used Claude to hack OpenAI employees' ChatGPT accounts https://www. theregister.com/security/2026/ 09/18/researchers-used-claude-to-hack-openai-employees-chatgpt-accounts/5297517 # ai
Researchers from the independent security platform Hacktron AI reported they used Anthropic's Claude tool to hack OpenAI's ChatGPT model. CBS News MoneyWatch reporter Megan Cerullo reports.
If OpenAI's best models are stymied by Claude's defenses and Claude's best models can't penetrate OpenAI, we'll all be better off. Let the foundation model red-teaming games begin! techcrunch.com/2026/09/18/r... Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reportin
https:// techcrunch.com/2026/09/18/rese archers-used-anthropics-claude-to-hack-into-openai/ # AISecurityBreach # CyberSecurity # OpenAI # Claude # VulnerabilityExploit # AchievementUnlocked (3/3)
🤖 Researchers used Anthropic's Claude Opus 5 to chain two flaws — in OpenAI's public help forum and its login system — taking over ChatGPT and Codex accounts of OpenAI staff and reaching an internal code repository, per Hacktron. 🔗 https:// thehackernews.com/2026/09/clau de-opus-5-helped-researchers-take.html # AISecurity # CyberSec