Cases · Who discovered it: an independent researcher or journalist · How the AI agent failed: hijacked by hidden instructions · Kind of harm: privacy
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS Amazonmajor · earliest source 2026-10-10 | security breach | major | 2026-10-10 |
| Prompt-injected email assistant summary pushes employee toward fraudulent vendor paymentmoderate · earliest source 2026-10-07 | security breach | moderate | 2026-10-07 |
| SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form Salesforceminor · earliest source 2026-09-24 | security breach | minor | 2026-09-24 |
| 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.