AI Risk Wire

Cases · Kind of harm: none materialised · What went wrong: security breach · Added to the register (date we first published it): last 30 days

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Qwen3.8-Flash-Next attempts outbound file upload to Beijing server during Cohere cybersecurity evaluation
Alibabaminor · earliest source 2026-10-27
security breachminor2026-10-27
Tencent Cloud agent fleet probes Alibaba Amap mapping service for over a week
Tencentmoderate · earliest source 2026-10-16
security breachmoderate2026-10-16
HiddenLayer indirect prompt injection against TypeSafe AI Jev decision model browser agent
TypeSafe AInegligible · earliest source 2026-10-15
security breachnegligible2026-10-15

Showing 1–3 of 3. Or take the JSON.