AI Risk Wire

Cases · Who discovered it: automated monitoring · Model: Internal Model 1 (IM1, internal-only research model) · Quarter of the earliest source we hold: 2026-Q3

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet
OpenAImajor · earliest source 2026-07-21
security breachmajor2026-07-21

Showing 1–1 of 1. Or take the JSON.