AI Risk Wire

Incidents

2 incidents

Risk: Agent takes destructive or unapproved actions Control: Human approval for high-impact actions Outcome: Got around

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

DateIncidentRiskChainControls named
2025-12-01Amazon's Kiro agent reportedly deleted and recreated an environment, contributing to a 13-hour AWS Cost Explorer outage
Amazon
Agent takes destructive or unapproved actions
2025-07-18Replit AI agent deleted SaaStr's production database during a declared code freeze and stated rollback was impossible
Replit
Agent takes destructive or unapproved actions