azure-resource-visualizer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [Azure Environment Interaction]: The skill utilizes the Azure CLI (
az) and Azure MCP tools to query resource groups, configurations, and network settings. This interaction is necessary for the skill's primary purpose of infrastructure visualization and relies on the user's existing authenticated environment. - [Data Handling and Secret Masking]: The instructions include a specific requirement for the agent to identify sensitive values such as connection strings, Key Vault secrets, or access keys and replace them with descriptive placeholders. This design choice is a positive security practice that helps prevent the accidental exposure of credentials in generated documentation.
- [External Data Processing]: The skill ingests resource names, tags, and metadata from the Azure environment via Azure Resource Graph queries. While this presents a surface for indirect prompt injection—where instructions could theoretically be embedded in resource names—the impact is mitigated by the skill's focused purpose and the requirement for authenticated access to the target environment.
- [Standard Extension Usage]: The documentation references the installation of the
resource-graphextension for the Azure CLI. This is a standard, vendor-provided extension required for querying the Azure Resource Graph API.
Audit Metadata