AI Risk Wire

Cases · How the AI agent failed: hijacked by hidden instructions · Model: Claude Sonnet 4.5

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
Anthropicmoderate · earliest source 2026-08-27
security breachmoderate2026-08-27

Showing 1–1 of 1. Or take the JSON.