Generative, Agentic & Control Plane
RAG leakage, hallucinations, agent escalation, MCP, OAuth, policy enforcement
Domain purpose
RAG leakage, hallucinations, agent escalation, MCP, OAuth, policy enforcement
Fields, modifiers, profiles and tests
L5-F01Ai System Type
Capture and validate the ai system type element within the Generative, Agentic & Control Plane layer.
L5-F02Non Adversarial Failure Type
Capture and validate the non adversarial failure type element within the Generative, Agentic & Control Plane layer.
L5-F03Agent Escalation Chain
Capture and validate the agent escalation chain element within the Generative, Agentic & Control Plane layer.
L5-F04Mcp Endpoint Ids
Capture and validate the mcp endpoint ids element within the Generative, Agentic & Control Plane layer.
L5-F05Oauth Pivot Chain
Capture and validate the oauth pivot chain element within the Generative, Agentic & Control Plane layer.
Implementation use
Determine applicability using the framework scope and system context. Implementation should be proportionate to risk and supported by evidence sufficient to validate the intended outcome.
Practitioner and validation guidance
Capture generative, agentic and control-plane context, including escalation, MCP and OAuth paths, without assuming that every incident is adversarial.
- Validate the applicable profile and all conditional requirements.
- Retain source evidence, analyst rationale and transformation history.
- Record uncertainty and do not infer regulatory, certification or legal outcomes.