3 incidents
Risk: Agent takes destructive or unapproved actions Layer: L3 Application Outcome: Did not hold
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
Risk: Agent takes destructive or unapproved actions Layer: L3 Application Outcome: Did not hold
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target