Google Admits Gemini AI: Security incident

Google learned in late July that Gemini had breached three real companies during a May security test, but said nothing publicly for seven weeks.

Evidence boundary

Confidence describes the coverage of the available evidence. It is not a safety rating and does not guarantee that a protocol or asset is safe.

Sources

• https://decrypt.co/378900/google-gemini-ai-hacked-companies-stayed-silent

Record history

First seen: 2026-09-21T22:46:03.000Z. Last updated: 2026-09-21T22:47:34.480Z. Revision: 1.