AI Risk Wire

Cases · How the AI agent failed: obeyed a harmful order · Themes: credential theft

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded
OpenAImajor · earliest source 2026-09-09
security breachmajor2026-09-09
Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies
Anthropicmajor · earliest source 2026-09-01
security breachmajor2026-09-01
Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltrationmajor · earliest source 2025-08-27security breachmajor2025-08-27

Showing 1–3 of 3. Or take the JSON.