Cases · Did an AI agent act: yes · Developer or organisation: Anthropic · What set it off: hidden instructions in its input
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document Anthropicmoderate · earliest source 2026-08-27 | security breach | moderate | 2026-08-27 |
| Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover Anthropicminor · earliest source 2026-08-05 | security breach | minor | 2026-08-05 |
Showing 1–2 of 2. Or take the JSON.