AI Risk Wire

Cases · Developer or organisation: Anthropic · How the AI agent failed: obeyed a harmful order · Quarter of the earliest source we hold: 2026-Q3

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Claude Code used by Yemen-based actors to develop guided-weapon GNC software
Anthropicmajor · earliest source 2026-09-14
produced harmful contentmajor2026-09-14
Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies
Anthropicmajor · earliest source 2026-09-01
security breachmajor2026-09-01

Showing 1–2 of 2. Or take the JSON.