Cases · Kind of harm: privacy · Severity: moderate · Themes: prompt injection
| 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 |
| Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document Anthropicmoderate · earliest source 2026-08-27 | security breach | moderate | 2026-08-27 |
| Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account OpenAImoderate · earliest source 2026-08-05 | security breach | moderate | 2026-08-05 |
Showing 1–3 of 3. Or take the JSON.