AI Risk Wire

Cases · Did an AI agent act: yes · Stage of use: in training · Who discovered it: an independent researcher or journalist

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft
OpenAImoderate · earliest source 2026-09-11
security breachmoderate2026-09-11

Showing 1–1 of 1. Or take the JSON.