azure-architecture

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation from the official Microsoft Learn domain.
  • Evidence: The skill contains an index of URLs pointing to learn.microsoft.com for reference architectures, solution ideas, and design patterns.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes external web content.
  • Ingestion points: The skill uses mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage to ingest external Markdown content into the agent's context.
  • Boundary markers: The skill does not define specific delimiters for the ingested content.
  • Capability inventory: The skill performs documentation retrieval and does not have access to dangerous capabilities like file system modification, privilege escalation, or shell command execution.
  • Sanitization: No explicit sanitization or filtering is described for the retrieved documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:30 AM