AI Risk Wire

Cases · What was exposed: personal information · Kind of harm: operations

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
Anthropicminor · earliest source 2026-08-05
security breachminor2026-08-05
Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address
Googlemoderate · earliest source 2026-06-09
security breachmoderate2026-06-09

Showing 1–2 of 2. Or take the JSON.