The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill contains a large volume of links to official Azure Monitor documentation hosted on the Microsoft Learn platform. All remote references target a trusted service provider and are integral to the skill's purpose as a documentation portal.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from remote documentation sources, which theoretically presents a surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through the execution of documentation fetching tools (microsoft_docs_fetch and fetch_webpage) referenced across all provided markdown files.
Boundary markers: The instructions do not define specific delimiters or security warnings to isolate the fetched external content from the agent's core instructions.
Capability inventory: The skill uses file reading capabilities and assumes the existence of network-capable documentation fetching tools.
Sanitization: There are no explicit sanitization or filtering steps defined for the content retrieved from the remote URLs. However, because the ingestion is scoped to a trusted organization (Microsoft), the risk is negligible.

azure-monitor