azure-role-selector
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided requirements to generate Azure CLI commands and Bicep infrastructure-as-code snippets. This represents a standard ingestion surface for untrusted data.\n
- Ingestion points: User requirements gathered in step 1 of the workflow (SKILL.md).\n
- Boundary markers: Not explicitly defined in the instructions.\n
- Capability inventory: Generates CLI commands and Bicep code via Azure MCP tools (SKILL.md).\n
- Sanitization: No explicit sanitization of user-provided strings is described.\n- [SAFE]: The skill adheres to security best practices by recommending least-privilege access and assigning permissions at the narrowest possible scope.\n- [SAFE]: All tool invocations target the official Azure MCP namespace, which is consistent with the skill's stated purpose and originates from a trusted cloud service provider environment.
Audit Metadata