azure-sql-virtual-machines
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves documentation from learn.microsoft.com using mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage. These connections are to a well-known and trusted service for documentation purposes.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes content fetched from external URLs. While no malicious behavior was detected, the ingestion of external data without explicit boundary markers or sanitization is an inherent risk factor for this functionality. Ingestion points: external content is retrieved from learn.microsoft.com via mcp_microsoftdocs and fetch_webpage. Boundary markers: No explicit delimiters are used to separate fetched content from agent instructions. Capability inventory: The skill uses read_file to access its own content. Sanitization: No sanitization or validation of the fetched content is specified.
Audit Metadata