azure-web-application-firewall
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates an attack surface by fetching external content from Microsoft Learn domains. However, because the content source is official documentation from the vendor, the risk is minimal.
- Ingestion points: Content is retrieved from
learn.microsoft.comviamcp_microsoftdocs:microsoft_docs_fetchorfetch_webpage. - Boundary markers: None explicitly defined in the skill instructions to delimit the fetched content.
- Capability inventory: The skill is limited to fetching and displaying markdown documentation.
- Sanitization: No specific sanitization methods for the external documentation are described.
- [EXTERNAL_DOWNLOADS]: Fetches technical documentation, configuration patterns, and best practices from official Microsoft Learn URLs to ensure the agent provides current information.
Audit Metadata