The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill is designed to retrieve documentation from learn.microsoft.com using tools like mcp_microsoftdocs:microsoft_docs_fetch. These are official, well-known Microsoft domains and services, and are considered safe.
[INDIRECT_PROMPT_INJECTION]: The skill processes external documentation in the agent's context. While this creates a data ingestion surface, the content is fetched exclusively from trusted Microsoft documentation sources. Furthermore, the skill does not request or demonstrate any dangerous capabilities such as file system modifications or arbitrary command execution that would facilitate a high-risk injection attack.
[SAFE]: All external resource references, including the GitHub repository link for the tool installation guide, point to official infrastructure belonging to the vendor (Microsoft). No malicious patterns such as obfuscation, persistence mechanisms, or privilege escalation were detected.

azure-virtual-network