microsoft-code-reference

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill includes functionality to fetch content from external Microsoft documentation URLs. While this constitutes a data ingestion surface, the source (learn.microsoft.com) is a trusted domain, and the skill lacks the dangerous capabilities (like file system writes or shell execution) required to exploit an injection.
  • [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded secrets, or unauthorized exfiltration patterns were identified.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill consists entirely of instructional markdown and does not package or execute any scripts or external binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 07:30 PM