azure-ddos-protection

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch remote documentation to provide up-to-date guidance.
  • It utilizes mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage as the primary mechanisms for retrieving content.
  • All destination URLs point to learn.microsoft.com, which is an official and trusted documentation service.
  • It references an installation guide for the mcp_microsoftdocs tool hosted on the official MicrosoftDocs GitHub repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it retrieves and processes content from external web pages.
  • Ingestion points: Documentation is fetched via URLs specified in the Category Index (e.g., learn.microsoft.com/en-us/azure/ddos-protection/...).
  • Boundary markers: The instructions do not explicitly define delimiters for the fetched content, though it is intended for informative reference.
  • Capability inventory: The skill facilitates Azure configuration and management tasks via the agent, but does not include direct file-writing or subprocess execution capabilities within its own instructions.
  • Sanitization: There are no explicit sanitization steps mentioned for the fetched Markdown content.
  • Since the ingestion source is a highly controlled, official documentation domain, the risk of malicious payload delivery is considered negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:21 PM