The Agent Skills Directory

[SAFE]: The skill retrieves technical documentation from learn.microsoft.com, which is a well-known and official Microsoft service. These network operations do not involve sensitive data and target a trusted domain.
[SAFE]: The skill provides a link to an installation guide on the MicrosoftDocs GitHub organization. This is a vendor-owned resource belonging to the skill's author and is used to provide legitimate configuration instructions.
[DATA_INGESTION]: This skill possesses an ingestion surface for potential indirect prompt injection as it fetches external documentation at runtime via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage.
Ingestion points: External documentation URLs from learn.microsoft.com listed in SKILL.md.
Boundary markers: None present; the skill instructs the agent to fetch and return the Markdown content directly.
Capability inventory: No dangerous internal capabilities (such as shell execution or file writes) are defined within the skill's own instructions.
Sanitization: None present in the skill instructions; it relies on the fetching tool's output and the agent's internal safety filters.

azure-industry