AI Risk Wire

Cases · What went wrong: security breach · Root cause: adversarial input · Severity: minor

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Indirect prompt injection attempts embedded in HTTP response headers across websitesminor · earliest source 2026-10-16security breachminor2026-10-16
Connecticut pro se plaintiff sanctioned for prompt injection against court AI toolminor · earliest source 2026-09-29security breachminor2026-09-29

Showing 1–2 of 2. Or take the JSON.