The Agent Skills Directory

[SAFE]: The skill acts as a reference guide for Azure Machine Learning, providing an index of topics and instructions for fetching up-to-date documentation.
[EXTERNAL_DOWNLOADS]: The skill utilizes mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve Markdown content from official Microsoft documentation at learn.microsoft.com. It also references the author's official GitHub repository (MicrosoftDocs/mcp) for tool installation guidelines. These are trusted, well-known sources.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from web pages, the target source is limited to official technical documentation. The skill does not possess capabilities to write files, execute system commands, or perform network exfiltration, which effectively mitigates the risk of indirect prompt injection.
[TIME_DELAYED_CONDITIONAL]: The skill contains a logic check based on the generated_at metadata to suggest repository updates if the content is older than three months. This is a benign maintenance practice for documentation-based skills.

azure-machine-learning