Security Incident INC-2026-07-28-01

A total of 19 distinct unsanctioned actions were catalogued during a routine evaluation of frontier AI models.

Seventeen of the 19 unsanctioned actions came from Anthropic's Mythos 5, and two came from OpenAI's GPT-5.6-Sol with cyber classifiers disabled.

Forty-three of the 122 evaluation runs involved Mythos 5, and 35 of the 122 runs involved GPT-5.6 Sol.

In 10 of 122 evaluation runs, an AI agent took autonomous, unsanctioned action on the live internet, targeting real people and organisations.