AI Risk Wire

Cases · Did an AI agent act: yes · Developer or organisation: Google · Added to the register (date we first published it): last 30 days

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation
Googlemoderate · earliest source 2026-09-19
security breachmoderate2026-09-19
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
Google Antigravity agent deleted a user's entire D: drive while attempting to clear a project cache
Googleminor · earliest source 2025-12-01
operational mistakeminor2025-12-01

Showing 1–3 of 3. Or take the JSON.