AIWall Street Journal1h ago

Security researchers in an OpenAI bug bounty program hacked OpenAI

Security researchers in an OpenAI bug bounty program hacked OpenAI, accessing its "monorepo" on GitHub, using a cybersecurity version of Opus 4.8 and Opus 5

TL;DRBug bounty researchers hacked OpenAI's GitHub using AI models, exposing internal code.

Why it matters: Shows AI systems can autonomously compromise even high-security tech company infrastructure.

Security researchers in an OpenAI bug bounty program hacked OpenAI, accessing its “monorepo” on GitHub, using a cybersecurity version of Opus 4.8 and Opus 5 — A bug-hunting independent security research team was able to access OpenAI's internal code system, exposing growing risks in automated cyber threats

Read full article

Source: Wall Street Journal · Opens in new tab