Cases · Did an AI agent act: yes · Kind of harm: privacy · How the AI was used: built into a product
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07 | security breach | moderate | 2026-10-07 |
| Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer Metamoderate · earliest source 2026-09-29 | leaked private data | moderate | 2026-09-29 |
| Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltrationmajor · earliest source 2025-08-27 | security breach | major | 2025-08-27 |
Showing 1–3 of 3. Or take the JSON.