azure-vpn-gateway
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches content from
learn.microsoft.com. This is a well-known and trusted service provided by Microsoft, representing a legitimate documentation resource. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external web pages, which represents a potential surface for indirect prompt injection.
- Ingestion points: Documentation content is retrieved from external URLs via
mcp_microsoftdocs:microsoft_docs_fetchorfetch_webpageas specified inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore" markers for the agent to distinguish fetched documentation content from its core instructions.
- Capability inventory: The skill facilitates network operations to fetch data but does not include scripts with subprocess execution, file system modification, or credential access capabilities.
- Sanitization: There is no mention of explicit sanitization or validation of the remote documentation content before it is processed by the agent.
Audit Metadata