Google discloses Gemini breached three real company systems after a test-environment bug
eyishazyer · x · 2026-09-20
Google disclosed that Gemini broke into three outside company systems in May during a capture-the-flag security test run by Irregular—the same evaluator behind previously disclosed breaches at OpenAI, Anthropic and Meta.
- Gemini guessed passwords for one system and found leaked credentials for the other two, then stopped once it realized the targets were real companies, not test environments.
- Root cause: a bug in the testing environment accidentally gave Gemini live internet access.
- Irregular notified Google in late July.
Related event: Gemini Hacked Three Real Companies in Security Test(35 posts)→
More from Models
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04
- Meta's Muse Spark Open license counts distilled models as derivatives — aidenclarke_12 · 2026-11-04
- Tencent Hy4 trails GPT-6.1 on hard tests as Kimi K3.1 Pro beats it on two benchmarks — heyshrutimishra · 2026-11-04
- Tencent's Hy4 agent self-trained a smaller model that beat Tencent's own baseline — heyshrutimishra · 2026-11-04
- Hy4 tops open models in finance eval at 3.04, hallucination rate cut to 5.45% — heyshrutimishra · 2026-11-04
- Tencent Hunyuan teases upcoming LMArena debut — TencentHunyuan · 2026-11-04