azure-files
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches content and documentation from official Microsoft Learn domains (learn.microsoft.com) and provides links to Microsoft's official GitHub repositories for tool installation.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection as it is designed to ingest and process data from external documentation pages.
- Ingestion points: External content is retrieved via the
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpagetools from the Microsoft Learn domain. - Boundary markers: The instructions do not specify explicit boundary markers or delimiters for the fetched documentation content.
- Capability inventory: The skill uses
read_fileto access local reference files and triggers network-based documentation fetching tools. - Sanitization: There is no explicit sanitization or filtering logic described for the external content before it is processed by the agent.
Audit Metadata