AI Risk Wire

Cases · Stage of use: in testing · Kind of harm: privacy · Themes: supply chain

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16security breachminor2026-10-16
OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet
OpenAImajor · earliest source 2026-07-21
AI pursued the wrong goalmajor2026-07-21

Showing 1–2 of 2. Or take the JSON.