Cases · Added to the register (date we first published it): last 30 days · Root cause: adversarial input · What set it off: hidden instructions in its input
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Indirect prompt injection attempts embedded in HTTP response headers across websitesminor · earliest source 2026-10-16 | security breach | minor | 2026-10-16 |
| Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07 | security breach | moderate | 2026-10-07 |
| Connecticut pro se plaintiff sanctioned for prompt injection against court AI toolminor · earliest source 2026-09-29 | security breach | minor | 2026-09-29 |
Showing 1–3 of 3. Or take the JSON.