make-custom-agent

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • Documentation-Focused Content: The skill serves as an instructional guide for scaffolding and configuring custom agents. It does not contain executable code or scripts that run automatically.
  • Trusted External References: The skill provides links to official Microsoft and GitHub documentation for chat participant APIs and Copilot extension guides, ensuring developers use verified resources.
  • Security Best Practices: Included in the validation checklist is a specific instruction to ensure agent definitions do not contain secrets, tokens, or internal URLs, which promotes secure configuration habits.
  • Standard Tool Usage: The configuration examples demonstrate the use of built-in tools like search, fetch, and codebase, which are standard capabilities within the Copilot ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 11:51 PM