azure-application-gateway
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to retrieve external documentation using
microsoft_docs_fetchorfetch_webpagefrom thelearn.microsoft.comdomain. Processing remote content introduces a surface where instructions embedded in the external pages could potentially influence the agent's behavior. - Ingestion points: Documentation URLs under
https://learn.microsoft.com/referenced in the Category Index. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within the fetched content.
- Capability inventory: The skill is designed for troubleshooting and configuration guidance, utilizing documentation fetching tools.
- Sanitization: No specific filtering or sanitization steps are defined for the retrieved documentation content.
- [EXTERNAL_DOWNLOADS]: The skill references numerous external links for documentation and tool installation.
- It directs the agent to fetch content from
learn.microsoft.comto provide up-to-date guidance. - It provides a link to an installation guide on
github.com/MicrosoftDocs/mcpfor themcp_microsoftdocstoolset.
Audit Metadata