The `azure-deploy` skill relies on custom, unaudited 'MCP Tools', posing a supply chain risk due to unknown
Claims to do
Azure Deploy: > **AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE** > > **PREREQUISITE**: The **azure-validate** skill **MUST** be invoked and completed with status `Validated` BEFORE executing this skill.
Actually does
This skill executes Azure deployments by orchestrating `azd up`, `azd deploy`, `terraform apply`, and `az deployment` commands. It reads `.azure/deployment-plan.md` for deployment plans and status, performs pre-deployment checks including RBAC health, and verifies post-deployment success and live RBAC roles. It utilizes `mcp_azure_mcp_azd`, `mcp_azure_mcp_subscription_list`, `mcp_azure_mcp_group_list`, and `azure__role` tools to interact with Azure.
The skill relies on several custom 'MCP Tools' (`mcp_azure_mcp_azd`, `mcp_azure_mcp_subscription_list`, `mcp_azure_mcp_group_list`, `azure__role`). The underlying implementation and security of these custom tools are not described, introducing a potential supply chain risk if they are not thoroughly audited and secured.
MCP Tools: `mcp_azure_mcp_subscription_list`, `mcp_azure_mcp_group_list`, `mcp_azure_mcp_azd`, `azure__role`
[](https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-deploy)<a href="https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-deploy"><img src="https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-deploy.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-deploy.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.