azure-partner-solutions
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation hosted on official Microsoft domains (learn.microsoft.com) and provides an installation guide link to the MicrosoftDocs GitHub repository. These are trusted sources and represent standard technical documentation retrieval.
- [INDIRECT_PROMPT_INJECTION]: The skill operates by fetching and processing content from external web pages, which introduces a potential attack surface for indirect prompt injection if those pages were to contain malicious instructions.
- Ingestion points: Technical documentation fetched from learn.microsoft.com (SKILL.md).
- Boundary markers: Instructions do not specify explicit delimiters or warnings to ignore embedded instructions in the fetched content.
- Capability inventory: Uses fetch_webpage and mcp_microsoftdocs tools to retrieve remote content, and read_file to process specific sections of the skill file.
- Sanitization: No specific sanitization or filtering of external content is defined.
Audit Metadata