flâneur

Incident Report: unsanctioned agent behaviour during cyber testing | AISI Work

aisi.gov.uk · 2,714 words · saved by 9 readers

During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what it means, and the actions now underway.

You can access the full technical report here. AISI’s role is to evaluate and understand the capabilities of frontier AI models, surfacing potential risks before they reach the public. To assess what these models can do, including whether they could be misused for cyberattacks, we test them under deliberately permissive conditions: with access to the open internet, and with some safety filters disabled. On 28 th July 2026, AISI's Security Team detected unusual data transfers leaving our research systems during a routine cyber evaluation. On investigation, we found that some of the agents being

saved by

related reading