azure-mgmt-apimanagement-dotnet
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and installs official Microsoft SDK packages (
Azure.ResourceManager.ApiManagementandAzure.Identity) from the NuGet registry. These are well-known and trusted dependencies for Azure infrastructure management. - [INDIRECT_PROMPT_INJECTION]: The code examples include patterns for ingesting local files (e.g.,
petstore-openapi.json) to define API schemas. This represents a potential surface for indirect prompt injection if an agent processes a malicious specification file. - Ingestion points:
references/apis-operations.mdusesFile.ReadAllTextto load external data. - Boundary markers: None are present in the provided boilerplate code snippets.
- Capability inventory: The skill enables resource creation and modification within the Azure management plane via the Azure Resource Manager SDK.
- Sanitization: No explicit sanitization or validation of the ingested content is demonstrated in the illustrative examples.
- [SAFE]: The skill reinforces security best practices by recommending the use of
DefaultAzureCredential(managed identity), warning against hardcoded secrets, and instructing users to avoid logging sensitive keys obtained from the API management service.
Audit Metadata