Cases · How the AI agent failed: hijacked by hidden instructions · Kind of harm: privacy · Added to the register (date we first published it): last 30 days
| 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 |
Showing 1–2 of 2. Or take the JSON.