The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses tools to fetch documentation content from learn.microsoft.com. As this is an official domain of a well-known and trusted service provider, these downloads are considered safe and are used purely for retrieving technical guidance.
[INDIRECT_PROMPT_INJECTION]: The skill incorporates external data into the agent's context by fetching documentation pages.
Ingestion points: Data is ingested via the mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage tools as described in SKILL.md.
Boundary markers: The instructions guide the agent to specific line ranges and topics, although strict delimiters for fetched content are not explicitly defined in the provided file.
Capability inventory: The skill possesses network read capabilities through the specified tools but lacks file-write or system execution capabilities.
Sanitization: The content is sourced from a trusted vendor repository, which minimizes the risk of malicious payload delivery through documentation.
[COMMAND_EXECUTION]: The skill contains no shell command execution or persistence mechanisms. It suggests the installation of the mcp_microsoftdocs tool via an official GitHub repository if the tool is missing, which is a legitimate developer workflow pattern.

azure-load-balancer