Hacking OpenAI

Automated excerpt

On July 25, 2026, we chained two critical vulnerabilities to compromise multiple OpenAI employees’ ChatGPT accounts. We started an Opus 4. 8 session with the Discourse Docker image and asked it to inspect the installed libheif package for security issues. Any deployment lacking the latest upstream security patches is potentially vulnerable.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.