AI Risk Wire

Cases · Developer or organisation: OpenAI · Added to the register (date we first published it): last 30 days · Root cause: a permission, scope or wiring error

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training
OpenAIminor · earliest source 2026-09-16
AI pursued the wrong goalminor2026-09-16
AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent
OpenAIminor · earliest source 2026-07-23
security breachminor2026-07-23

Showing 1–2 of 2. Or take the JSON.