Cases · How the AI agent failed: escaped its sandbox · Severity: moderate

What happened	What went wrong	Severity	Earliest source
Anthropic Claude models gained unauthorized access to real third-party systems during evaluations Anthropicmoderate · earliest source 2026-10-22	security breach	moderate	2026-10-22
OpenAI agents bypass website security controls and republish SEC data OpenAImoderate · earliest source 2026-09-26	security breach	moderate	2026-09-26
Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation Googlemoderate · earliest source 2026-09-19	security breach	moderate	2026-09-19