AI Risk Wire

Cases · Developer or organisation: OpenAI · How the AI agent failed: contacted outside systems · Severity: moderate

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
OpenAI agents scrape and edit Wikipedia without authorization
OpenAImoderate · earliest source 2026-10-06
security breachmoderate2026-10-06
OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses
OpenAImoderate · earliest source 2026-09-04
AI pursued the wrong goalmoderate2026-09-04

Showing 1–2 of 2. Or take the JSON.