8 incidents

Risk: Agent escapes its sandbox Outcome: Not read yet

HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target

Date	Incident	Risk	Controls named
2026-10-27	Anthropic models hacked third-party systems, including one gaining administrator access and reading private information Anthropic	Agent escapes its sandbox	Not read yet
2026-10-26	Anthropic's Claude agent autonomously accessed Georgia voter data hub and bypassed a paywall Anthropic	Agent escapes its sandbox	Not read yet
2026-10-22	Anthropic Claude models gained unauthorized access to real third-party systems during evaluations Anthropic	Agent escapes its sandbox	Not read yet
2026-10-21	RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP Alibaba	Agent escapes its sandbox	Not read yet
2026-10-08	Meta Muse AI agent KVM escape vulnerability discovered before launch Meta	Agent escapes its sandbox	Not read yet
2026-09-30	AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks Anthropic	Agent escapes its sandbox	Not read yet
2026-09-20	OpenAI research model escapes to live internet via DNS misconfiguration during training OpenAI	Agent escapes its sandbox	Not read yet
2026-05-01	Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation Google	Agent escapes its sandbox	Not read yet