azure-ai-services

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch documentation from learn.microsoft.com using tools like mcp_microsoftdocs. These sources are well-known and official Microsoft domains.
  • [SAFE]: (Indirect Prompt Injection Surface Analysis)
  • Ingestion points: The skill retrieves external Markdown content from learn.microsoft.com (SKILL.md).
  • Boundary markers: Absent; the skill does not specify delimiters for fetched content.
  • Capability inventory: None; the skill provides information only and does not contain executable scripts, subprocess calls, or file-write operations.
  • Sanitization: Absent; the skill relies on the agent's internal handling of fetched documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 10:08 AM