An analyst observes a user-originated instruction submitted to an AI application that attempts to override protected instructions or operational constraints. Within the same authenticated interaction, the AI system subsequently attempts a tool invocation, resource access, or workflow transition inconsistent with the authorized task or capability scope. The analyst correlates the originating instruction, subsequent operation, and authorization context to identify a potential successful instruction-boundary violation.
| Data Component | Name | Channel |
|---|---|---|
| Application Log Content (DC0038) | m365:unified | CopilotInteraction |
| Field | Description |
|---|---|
| ProtectedInstructionBoundaries | Instructions and operational constraints that user-originated input cannot supersede |
| AuthorizedAIWorkflows | Permitted task sequences and workflow transitions |
| AICapabilityScopes | Authorized tools, operations, resources, and actions for each actor or agent role |
| InstructionToActionWindow | Maximum interval between the submitted instruction and subsequent operation |
| RequiredInteractionCorrelation | Required actor, session, interaction, or trace identifiers linking the observations |
| MinimumOverrideEvidence | Evidence required to classify an instruction as an attempted authority override |
| AuthorizedAdversarialTesting | Approved testing identities and execution contexts |