azure-nat-gateway
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 from 'learn.microsoft.com' using specific MCP tools or a web fetching fallback. It also references a tool installation guide located in the 'MicrosoftDocs' GitHub repository. These sources are official documentation platforms and trusted repositories.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation from external web sources, creating a surface where instructions embedded in the retrieved content could potentially influence agent behavior. However, because the ingestion is targeted at official and trusted documentation domains, the risk is negligible.
- Ingestion points: Documentation content is retrieved at runtime from URLs listed in 'SKILL.md' using 'microsoft_docs_fetch' or 'fetch_webpage'.
- Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to ignore potentially malicious embedded content in the fetched markdown.
- Capability inventory: The skill utilizes 'read_file', 'mcp_microsoftdocs:microsoft_docs_fetch', and 'fetch_webpage'.
- Sanitization: There are no explicit sanitization or filtering steps defined for the external content before it is processed by the agent.
Audit Metadata