azure-resource-visualizer
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Azure CLI (
az) and MCP tools to gather architectural metadata from the user's resource groups. These operations are strictly read-only and require explicit user selection of the resource group. - [DATA_EXFILTRATION]: While the skill accesses sensitive architectural details, its design ensures that all processed information remains within the agent's environment, resulting in local markdown and Mermaid diagram files. No network exfiltration patterns were detected.
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by processing external data from Azure tool outputs. * Ingestion points: Azure CLI and MCP tool output (SKILL.md); * Boundary markers: Absent; * Capability inventory: Azure CLI execution and file system writes (SKILL.md); * Sanitization: Absent. This is considered a low-risk surface given the specific architectural visualization use case.
- [SAFE]: The skill implements safety boundaries by explicitly prohibiting the modification or deletion of Azure resources and following a structured analysis workflow that involves the user.
Audit Metadata