All incidents / Google
Google AI security incidents
3 security incidents involving Google's AI since January 2025, including 3 where an agent acted on its own. The model was judged at fault in 2. Involvement does not mean Google was responsible.
| 18 Sep 2026 | Google's Gemini accessed three companies' systems during a security evaluation Undisclosed (three companies) | Agent misbehaviour | Low |
| 1 Dec 2025 | Google's Antigravity agent wiped a user's entire drive while clearing a cache Individual user | Agent misbehaviour | Medium |
| 25 Jul 2025 | Gemini CLI destroyed a user's files after misreading a failed command Individual user | Agent misbehaviour | Medium |