azure-data-box-family
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official Microsoft domains using dedicated tools (
microsoft_docs_fetchandfetch_webpage). It also references the official MicrosoftDocs GitHub repository for tool installation and updates. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests content from external URLs to provide documentation to the user.
- Ingestion points: Documentation URLs listed in the category tables and the
microsoft_docs_fetchtool instructions inSKILL.md. - Boundary markers: None identified in the prompt instructions to the agent; the agent is simply instructed to return markdown content.
- Capability inventory: The skill utilizes
read_fileand network-enabled tools likefetch_webpageandmicrosoft_docs_fetchto retrieve external data. - Sanitization: None identified; the skill assumes the content returned by official documentation sources is safe and relies on the agent's internal filters for the final response.
Audit Metadata