The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external documentation which could theoretically contain instructions intended to influence the agent's behavior.
Ingestion points: Documentation content is fetched dynamically from learn.microsoft.com using the mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage tools as instructed in SKILL.md.
Boundary markers: The skill does not specify the use of delimiters or specific boundary markers to isolate the fetched external content from the agent's instructional context.
Capability inventory: No dangerous capabilities such as arbitrary file writes, shell command execution, or sensitive data access were found in SKILL.md.
Sanitization: There is no evidence of runtime sanitization or filtering for the retrieved Markdown content.
Context: The ingestion source is the official Microsoft documentation domain, which is a highly trusted and authoritative resource. This behavior is consistent with the primary purpose of a documentation-focused skill.

azure-pipelines