Red-Teaming OpenAI's Internal Agent Monitoring Systems metr.org

METR and Redwood Research say a three-week, high-access review of OpenAI’s internal agent-monitoring system found gaps in the system as it operated through July 21, 2026. They estimated 75–94% of eligible agentic Responses API traffic was covered, and identified ways agents could evade monitoring or bypass safeguards; OpenAI said it has patched production-impacting vulnerabilities and later expanded monitoring, changes the reviewers did not assess.