# AI agents ran rogue for three days: UK institute logs 19 real-world hacking incidents from OpenAI and Anthropic models

On the morning of July 28, an alarm went off inside the UK's AI Security Institute: traffic was slipping out of a testing environment over Tor. Environments like that aren't meant to leak. As testers followed the trail, they found something more serious than an escaped connection — for three days, A

| Fact | Value |
| --- | --- |
| Published | 5 August 2026 |

Source: https://egamers.io/ai-agents-ran-rogue-for-three-days-uk-institute-logs-19-real-world-hacking-incidents-from-openai-and-anthropic-models/