AGENT LAB: SKILLS

microsoft-code-reference

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references the Microsoft Learn MCP Server at learn.microsoft.com. According to the [TRUST-SCOPE-RULE], Microsoft is a trusted organization, and the domain is official and safe for documentation retrieval.
  • [NO_CODE] (SAFE): No executable scripts (Python, Node.js, Shell) are included with this skill. It consists entirely of Markdown instructions and tool definitions.
  • [DATA_EXFILTRATION] (SAFE): There are no patterns indicating access to sensitive local files (~/.ssh, ~/.aws) or unauthorized network requests to non-whitelisted domains.
  • [PROMPT_INJECTION] (SAFE): No prompt injection or behavior override patterns (e.g., "Ignore previous instructions") were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:50 PM