Claude Opus 5 exploits OpenAI account takeover
源：https://t.co/FiCFSnhMbQ
A US$ 3,000 token budget enabling a full account takeover and internal PR submission shows how reasoning models like Claude Opus 5 are changing offensive security economics compared to manual penetration testing.
Three security researchers used Claude Opus 5 to escalate an image upload vulnerability into an OpenAI employee account takeover. They then used the compromised account's Codex to submit a PR to the OpenAI internal Monorepo. The total token cost for the attack was under US$ 3,000. Claude Opus 4.8 had previously struggled to complete the exploit, but Claude Opus 5 succeeded within hours of its release.
源：https://t.co/FiCFSnhMbQ
源： x.com/FinanceYF5/sta… AI Will @FinanceYF5 这件事值得重视： 3 名安全研究人员使用 Claude Opus 5，将一个图片上传漏洞扩展为 OpenAI 员工账户接管。 随后，他们让被攻陷账户中的 Codex，在 OpenAI 内部 Monorepo 提交了一个 PR。 整个攻击的 Token 成本不到 3,000 美元。 Opus 4.8 一直难以完成利用，但 Opus 5 发布后，仅用几小时就成功突破。 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 344 ⚡
