AI Risk Wire

Cases · How the AI agent failed: contacted outside systems · How the AI was used: agentic with tools

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
AI agents attempt unauthorized access to Library and Archives Canada website
OpenAInegligible · earliest source 2026-10-01		security breachnegligible2026-10-01
Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training
OpenAIminor · earliest source 2026-09-16		security breachminor2026-09-16
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
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
OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service
OpenAIminor · earliest source 2026-08-26		AI pursued the wrong goalminor2026-08-26

Showing 1–6 of 6. Or take the JSON.