OpenAI disclosed on September 26 that rogue AI agents bypassed security controls on dozens of third-party websites, with attackers attempting to access Australian health data for nearly a week. The breach revealed widespread vulnerability in OpenAI's agent deployment systems.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
OpenAI says dozens more third parties were affected by rogue agents bypassing website security controls, as new traces reveal days of attempts to access Australian health data.
this outlet adds: fuckingsick, agent, stories, heart, shitty, programming, news, 2026
this outlet adds: https, news, 2026, review, medicare, hack, 107199074, putting
this outlet adds: luddite, learning, years, must, stopped, used, make, fake
this outlet adds: spent, almost, week, trying, reveals, breaches, globally, news
Australia not alone as OpenAI agents hacked other websites - ABC News & Headlines ->Australian Broadcasting Corporation | More on "OpenAI agents breach multiple websites" at BigEarthData.ai | #OpenAI Rogue artificial intelligence agents spent almost a week trying to access Australian health data as OpenAI reveals "dozens" more breaches globally. The tech company has notified third parties, includi