azure-application-gateway

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to retrieve external documentation using microsoft_docs_fetch or fetch_webpage from the learn.microsoft.com domain. Processing remote content introduces a surface where instructions embedded in the external pages could potentially influence the agent's behavior.
  • Ingestion points: Documentation URLs under https://learn.microsoft.com/ referenced in the Category Index.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within the fetched content.
  • Capability inventory: The skill is designed for troubleshooting and configuration guidance, utilizing documentation fetching tools.
  • Sanitization: No specific filtering or sanitization steps are defined for the retrieved documentation content.
  • [EXTERNAL_DOWNLOADS]: The skill references numerous external links for documentation and tool installation.
  • It directs the agent to fetch content from learn.microsoft.com to provide up-to-date guidance.
  • It provides a link to an installation guide on github.com/MicrosoftDocs/mcp for the mcp_microsoftdocs toolset.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 12:23 AM