AI Risk Wire

Cases · How the AI agent failed: took data out · Added to the register (date we first published it): last 30 days · Severity: major

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems
OpenAImajor · earliest source 2026-09-25
security breachmajor2026-09-25

Showing 1–1 of 1. Or take the JSON.