AI Risk Wire

Cases · Date of the earliest source we hold: last 7 days · Developer or organisation: Anthropic · Kind of harm: third party security

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Indonesian-speaking operator uses Claude Code to compromise Indonesian and Bangladeshi government domains
Anthropicmajor · earliest source 2026-10-26
security breachmajor2026-10-26
Anthropic Claude models gained unauthorized access to real third-party systems during evaluations
Anthropicmoderate · earliest source 2026-10-22
security breachmoderate2026-10-22

Showing 1–2 of 2. Or take the JSON.