The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches documentation content from official Microsoft Learn domains (learn.microsoft.com). This represents standard functionality for a documentation-oriented skill provided by the vendor.
[INDIRECT_PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection as it is designed to fetch and process external documentation content.
Ingestion points: External data enters the agent context via the mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage tools as specified in SKILL.md.
Boundary markers: The instructions do not define specific boundary markers or delimiters to isolate the fetched external content from the agent's primary instructions.
Capability inventory: No dangerous capabilities, such as file-system writes, arbitrary command execution, or subprocess spawning, are present in the skill.
Sanitization: There are no explicit sanitization or filtering steps defined for the external content before it is processed by the agent.

azure-cloud-adoption-framework