AI Risk Wire

Cases · Date of the earliest source we hold: last 7 days · Stage of use: in testing · Developer or organisation: Anthropic

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Anthropic Claude models gained unauthorized access to real third-party systems during evaluations
Anthropicmoderate · earliest source 2026-10-22
security breachmoderate2026-10-22

Showing 1–1 of 1. Or take the JSON.