writing-bicep-templates
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and templates for Azure infrastructure development with a focus on security. It explicitly recommends against using admin credentials or secrets, favoring Azure Managed Identities for resource access (e.g., ACR pull).
- [SAFE]: The infrastructure configurations included in the standards enforce security hardening, such as disabling insecure (HTTP) ingress and using scoped identity assignments.
- [SAFE]: The command examples provided—specifically 'az bicep build' and 'az deployment group what-if'—are standard, benign validation utilities used by Azure developers to verify infrastructure code.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for generating infrastructure code from user requirements. While the guidance is secure, the agent's ingestion of external requirements creates a potential surface for indirect injection.
- Ingestion points: User infrastructure requirements and existing Bicep files within the workspace.
- Boundary markers: None explicitly specified in the skill body.
- Capability inventory: Execution of Azure CLI ('az') commands for building and deploying templates.
- Sanitization: The skill does not provide specific sanitization rules for user-supplied values used in generated templates.
Audit Metadata