AI Risk Wire

Cases · What was exposed: credentials · Quarter of the earliest source we hold: 2026-Q3 · Root cause: a safeguard that was in place did not hold

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
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
OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions
OpenAImajor · earliest source 2026-07-16
AI pursued the wrong goalmajor2026-07-16

Showing 1–2 of 2. Or take the JSON.