AI Risk Wire

Cases · Quarter of the earliest source we hold: 2026-Q3 · Added to the register (date we first published it): last 30 days

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Bee Cheng Hiang mass marketing e-mail exposes 95,000 customer addresses after AI-generated code omitted recipient hidingmoderate · earliest source 2026-09-30leaked private datamoderate2026-09-30
AI-generated sexually explicit deepfake smear campaign against Porsche sales consultant Mu Qianwenmoderate · earliest source 2026-09-30produced harmful contentmoderate2026-09-30
Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer
Metamoderate · earliest source 2026-09-29
leaked private datamoderate2026-09-29
Connecticut pro se plaintiff sanctioned for prompt injection against court AI toolminor · earliest source 2026-09-29security breachminor2026-09-29
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
AI pursued the wrong goalmajor2026-07-21

Showing 1–6 of 6. Or take the JSON.