azure-internet-peering

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: All external references, including documentation links and tool installation guides, point to official Microsoft domains such as learn.microsoft.com and github.com/MicrosoftDocs.
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch markdown documentation from learn.microsoft.com. This is a well-known, trusted service and the behavior is expected for the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill contains operational instructions for the agent to manage its internal state and recommend tool updates. It also defines a surface for indirect prompt injection by processing external web content. However, the risk is mitigated as the source is a highly trusted official vendor site.
  • Ingestion points: External content fetched from learn.microsoft.com via documentation tools.
  • Boundary markers: Absent.
  • Capability inventory: Network access for documentation retrieval via specified tools.
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:41 AM