azure-advisor

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official Microsoft domains and refers to a repository from the author, MicrosoftDocs. These are trusted sources.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes content from external documentation URLs.
  • Ingestion points: Documentation content is fetched from 'learn.microsoft.com' as defined in SKILL.md.
  • Boundary markers: No specific delimiters or instructions for the agent to ignore embedded instructions are present.
  • Capability inventory: The skill uses 'read_file' to access local context and 'microsoft_docs_fetch' to retrieve remote data.
  • Sanitization: No explicit sanitization of remote documentation content is defined, as the source is trusted.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:31 AM