TechAnthropic’s Claude helped 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.
C
CryptoSlate★★★☆☆2026-09-19 00:40Original
Anthropic’s Claude helped researchers breach OpenAI in under 72 hours
Tech