Where SentinelleIA sits across the seven MAESTRO layers

MAESTRO is the Cloud Security Alliance threat model for agentic AI systems, published in July 2025. It decomposes an agentic system into seven layers, from the model itself up to the ecosystem of agents that call each other. This document places our coverage on each of them.

• The full L1 to L7 table: what each layer covers, and which control operates there.
• Why the supervisor is named apart from the nine agents, and what that answers.
• What the mapping does not claim, stated explicitly rather than implied.
• The measured attack success rate, direct against shielded, with the false positive cost.

Two pages, PDF, English. Written for security architects and analysts who want the structure before the sales call.