← All steps
Part B · Step 6

Security review

Owner
Security team.
Input
Agent Card complete.

Owner: Security team. Input: Agent Card complete. Sub-steps:

  1. Required for all Medium- and High-risk agents. Optional for Low-risk (CoE Lead decides).
  2. Apply Microsoft CAF's Discover phase (framework.md §25.1):
    • Threat-model the agent. Use STRIDE; supplement with MITRE ATLAS and OWASP Generative AI risk lists.
    • Walk through: prompt injection paths, data poisoning paths, model inversion, jailbreak paths, data exfiltration paths.
  3. Check data boundaries. Where does sensitive data flow? Where does it stop? Does the agent need every field it's been granted, or can scope be narrowed?
  4. Plan adversarial testing. What red-team scenarios will run before pilot?
  5. Plan DLP (data loss prevention): what content filters are needed on inputs/outputs?
  6. Confirm communication-channel security: managed identities, private endpoints, secured MCP server endpoints.

Output / gate criteria: Security signs off on a documented threat model + planned mitigations + planned red-team scenarios.

Decision branches:

  • Security finds a blocker (e.g., agent would access regulated data without DLP) → back to Step 5 to revise the Agent Card.

Skip-this-step risk: Prompt injection lands in production; PII flows somewhere it shouldn't; an attacker turns the agent into an insider.