azure-rbac
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill possesses an ingestion surface for untrusted user input which is used to generate CLI and Bicep code. Ingestion points: User descriptions of desired permissions in the skill prompt. Boundary markers: Absent. Capability inventory: Generates CLI and Bicep code via internal tools like azure__extension_cli_generate and azure__bicepschema. Sanitization: Not explicitly defined, though the skill focuses on generation rather than execution.
Audit Metadata