Fixed-scope engagement
Agentic AI Security Assessment
Every agent in your tenant, what each one can read and do, and whether your assurance panel should sign off the deployment.
- Typical duration
- 2–3 weeks
What you get
- 1Agent inventory across the tenant with a named owner per agent: Copilot Studio, Foundry Agent Service, and third-party agents holding Microsoft Graph or API access
- 2Injection surface map per agent: what untrusted content it reads, what data it can reach, and what actions it can take
- 3Identity and permission review across Microsoft Entra ID: agent identities, service principals, delegated versus application permissions, and RBAC on grounding data
- 4Data flow review for assurance: where inference runs, what prompts are logged and retained, and the inputs your DPIA and Algorithmic Transparency Recording Standard record need
- 5Controls verification: seeded prompt injection payloads run against deployed agents in an agreed window, with each control's response recorded
- 6Findings register mapped to the NCSC Cyber Assessment Framework and the OWASP Top 10 for LLM Applications, with remediation expressed as deployed controls, pipeline gates, or scheduled reviews with named owners
Outcome
Either a deployment your assurance panel can sign off, or a written account of what has to change before it can.
Other fixed-scope engagements
Finding the agents first
The assessment begins with an inventory: the agents you know about, the platforms they run on and what each one can reach. That decides which parts of the estate to cover first. The assessment takes two to three weeks.