Skip to main content

Buyer guide

Copilot Studio Security, Data & Residency Checklist

How data policies, Purview audit, customer-managed keys and data location apply to agents, and the agent security risks researchers have shown.

Reading time
1 min read
Sources
10 cited

Apply data policies to every environment, keep audit logs in Purview, check where data rests and which models process it, and test every agent against prompt injection before it reads real data.

When you need this

  • An agent will read customer or employee records through connectors.
  • Security asks how agents are audited and where their data lives.
  • An agent will accept input from email, a website or another channel outside the tenant.

Evaluation criteria

  1. Data policies

    Which connectors can each agent use?

    Look forPower Platform data policies apply to all tenants with no agent exemption. Block connectors agents do not need.

  2. Audit

    Is agent activity recorded?

    Look forCopilot Studio writes audit logs to Microsoft Purview; review them with your security team.

  3. Data location and models

    Where does agent data rest, and which models process it?

    Look forData stays in the tenant's geography, or the United States when the tenant's location is not listed. Models marked cross-geo can process data outside the region.

  4. Prompt injection

    Can an outsider steer the agent?

    Look forZenity Labs showed an email-triggered agent connected to Salesforce exfiltrating data, Tenable got an agent to leak card data, and Datadog Security Labs showed agent pages used to phish OAuth tokens. Test each channel that can reach your agent.

  5. Encryption and compliance

    Do you need customer-managed keys or a compliance program?

    Look forCopilot Studio supports customer-managed keys for environment data, and Microsoft lists its ISO, SOC and HIPAA coverage.

Questions to ask vendors

  1. Which agents accept input from outside the tenant?
  2. Which connectors does each agent hold, and does it need them all?
  3. Which models are allowed in each environment?
  4. Who reviews Copilot Studio audit logs?

Red flags

  • An email-triggered agent with write access to a CRM.
  • Cross-geo models allowed for data that must stay in region.
  • Agents shared to the whole tenant by default.
  • No prompt injection test before launch.

Products in this piece

Sources

Official documentation
7
Public source
3
  1. Microsoft Learn: Configure data policies for agentsOfficial documentationlearn.microsoft.com
  2. Microsoft Learn: View Copilot Studio audit logs in PurviewOfficial documentationlearn.microsoft.com
  3. Microsoft Learn: Data locations in Copilot StudioOfficial documentationlearn.microsoft.com
  4. Microsoft Learn: Select a primary AI model for your agentOfficial documentationlearn.microsoft.com
  5. Microsoft Learn: Customer-managed encryption keys for Copilot StudioOfficial documentationlearn.microsoft.com
  6. Microsoft Learn: Review ISO, SOC, and HIPAA complianceOfficial documentationlearn.microsoft.com
  7. Microsoft Learn: Security and governance in Copilot StudioOfficial documentationlearn.microsoft.com
  8. Zenity Labs: A Copilot Studio story 2, when AIjacking leads to full data exfiltration (Jul 7, 2025)Public sourcelabs.zenity.io
  9. Tenable: Microsoft Copilot Studio security risk, how simple prompt injection leaked sensitive data (Dec 11, 2025)Public sourcetenable.com
  10. Datadog Security Labs: CoPhish, using Microsoft Copilot Studio as a wrapper (Oct 20, 2025)Public sourcesecuritylabs.datadoghq.com