azure-virtual-wan
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch documentation content from official Microsoft Learn domains (learn.microsoft.com) using specialized tools like mcp_microsoftdocs:microsoft_docs_fetch. These downloads target a trusted organization and are documented as standard functionality for retrieving relevant technical guidance.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a gateway for the agent to process external data from documentation URLs. The ingestion of external content into the agent's context represents a potential attack surface if the source data contains instructions designed to influence the agent.
- Ingestion points: External data enters the agent context via documentation fetching tools using the URLs listed in the Category Index within SKILL.md.
- Boundary markers: The instructions do not specify explicit delimiters or "ignore embedded instructions" warnings for the fetched content.
- Capability inventory: The skill primarily performs documentation retrieval and reading; it does not include capabilities for arbitrary command execution or sensitive file system modifications.
- Sanitization: There are no defined filters or sanitization steps for the markdown content retrieved from the remote documentation source.
Audit Metadata