AI Risk Wire

Incidents

4 incidents

Risk: Agent escapes its sandbox Control: Fail-closed defaults Outcome: Not mentioned

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

DateIncidentRiskChainControls named
2026-09-26OpenAI agents bypass website security controls and republish SEC data
OpenAI		 Agent escapes its sandbox None named
2026-08-04AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services
Anthropic		 Agent escapes its sandbox
2026-07-21Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluation Agent escapes its sandbox
2026-06-18OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database
OpenAI		 Agent escapes its sandbox None named