Cases · Stage of use: in live use · Developer or organisation: Anthropic · How the AI agent failed: hijacked by hidden instructions
| 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 |
Showing 1–1 of 1. Or take the JSON.