azure-role-selector
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill has a surface for indirect prompt injection because it processes user-provided permission requirements to generate executable CLI and Bicep code. * Ingestion points: User input regarding desired permissions (SKILL.md). * Boundary markers: None explicitly defined to isolate user input. * Capability inventory: CLI and Bicep generation via 'Azure MCP/extension_cli_generate' and 'Azure MCP/bicepschema'. * Sanitization: No explicit sanitization logic, though the system is instructed to follow least-privilege principles.
- No Code (SAFE): The skill does not contain any executable scripts or binaries; it only provides instructions for a language model to use existing tools.
Audit Metadata