AI Risk Wire

Cases · Quarter of the earliest source we hold: 2026-Q3 · Added to the register (date we first published it): today

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenClaw agent exploited a gym booking API to cancel another member's reservation while moving its user up a waitlist
Anthropicmoderate · earliest source 2026-08-10
AI pursued the wrong goalmoderate2026-08-10
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 1–2 of 2. Or take the JSON.