Cases · Stage of use: in live use · Who discovered it: an independent researcher or journalist · Severity: moderate
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Deepfake investment-scam ads impersonating Nigerian public figures on Facebookmoderate · earliest source 2026-10-08 | other | moderate | 2026-10-08 |
| Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07 | security breach | moderate | 2026-10-07 |
| Guardian test: ChatGPT and Grok remove hijab from AI-generated image of Muslim woman OpenAImoderate · earliest source 2026-10-01 | produced harmful content | moderate | 2026-10-01 |
| Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document Anthropicmoderate · earliest source 2026-08-27 | security breach | moderate | 2026-08-27 |
Showing 1–4 of 4. Or take the JSON.