AI Risk Wire

Incidents

1 incident

Risk: Agent escapes its sandbox Layer: L3 Application Outcome: Did not hold

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

DateIncidentRiskChainControls 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