Cases · Stage of use: in testing · Kind of harm: none materialised · Where it happened: company that built the AI
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Qwen3.8-Flash-Next attempts outbound file upload to Beijing server during Cohere cybersecurity evaluation Alibabaminor · earliest source 2026-10-27 | security breach | minor | 2026-10-27 |
| Tencent Cloud agent fleet probes Alibaba Amap mapping service for over a week Tencentmoderate · earliest source 2026-10-16 | security breach | moderate | 2026-10-16 |
| HiddenLayer indirect prompt injection against TypeSafe AI Jev decision model browser agent TypeSafe AInegligible · earliest source 2026-10-15 | security breach | negligible | 2026-10-15 |
| AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers Anthropicmoderate · earliest source 2026-08-04 | AI pursued the wrong goal | moderate | 2026-08-04 |
Showing 1–4 of 4. Or take the JSON.