microsoft-docs

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Trusted Documentation Sources: The skill exclusively directs the agent to query official and well-known domains owned by Microsoft, such as learn.microsoft.com, aspire.dev, code.visualstudio.com, and docs.github.com. References to these repositories and domains are considered safe as they belong to the skill's author and established technology services.
  • Administrative Tooling References: The instructions mention standard CLI commands like aspire update to ensure the user's environment is compatible with the latest documentation search features. These are provided as informative guidance for the user within the context of managing official Microsoft development tools.
  • Data Ingestion Surface: The skill is designed to fetch and interpret documentation from the web to answer user queries. While these are trusted sources, processing external content is an inherent part of the skill's operation.
  • Ingestion points: External content is retrieved via tools such as microsoft_docs_fetch, get_doc, and mcp_context7_query-docs (SKILL.md).
  • Boundary markers: The skill does not explicitly define delimiters or specific "ignore instructions" warnings for the fetched documentation content.
  • Capability inventory: No file system modifications, arbitrary code execution, or network exfiltration capabilities are defined within this skill's instructions.
  • Sanitization: There are no explicit sanitization or filtering steps described for the retrieved documentation text before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 11:04 AM