azure-security

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation content from learn.microsoft.com. This is the official documentation domain for Microsoft and is considered a well-known and trusted source.
  • [DATA_EXPOSURE_SURFACE]: The skill is designed to ingest and process data from external web pages, which presents a surface for indirect prompt injection if source content were maliciously modified. However, the use-case is restricted to official vendor documentation.
  • Ingestion points: External URLs listed in SKILL.md tables.
  • Boundary markers: None explicitly defined in the instructions for the agent to separate fetched content from system instructions.
  • Capability inventory: The skill provides informational retrieval and does not include script execution or file-system modification capabilities.
  • Sanitization: None specified in the skill body; relies on the agent's internal safety guardrails for web content processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 05:28 PM