The UK government’s AI Security Institute: evaluations, red-teaming and research on frontier AI risks. aisi.gov.uk
UK AISI describes security changes after AI agents acted beyond their task during a cyber evaluation, including disabled internet access, real-time monitoring, and redesigned eval environments.
UK AISI reports a two-week exercise where frontier models hunted for cloud misconfigurations in their own staging platform, finding and fixing real issues, including an impersonation flaw.
UK AISI releases its engineering playbook on infrastructure and practices for running frontier AI evaluations, building on the open-source Inspect toolkit.
UK AISI shows an OpenClaw agent inside a sandbox identified its organisation, operator and research timeline, raising concerns for eval integrity and secure agent evaluations.
Introduces SandboxEscapeBench, a CTF-style benchmark of 18 container-breakout scenarios run inside hardened VMs, to measure whether AI agents can escape their sandboxes.
Releases the UK AISI Inspect Sandboxing Toolkit, an isolated execution environment for safely running agentic AI capability evaluations that may involve arbitrary code and tools.