msresearch-promptions

Pass

Audited by Gen Agent Trust Hub on May 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Infrastructure Automation: The skill features a utility script (provision-azure-openai.sh) that automates the setup of Azure OpenAI resources using the Azure CLI. This process is transparently documented and includes user-prompted confirmation for resource creation and deployment.
  • Configuration Management: The provisioning script handles sensitive configuration by writing API keys and endpoints to local .env files. This is a standard practice for local development, and the skill includes mechanisms for file backups and instructions for maintaining secret hygiene.
  • Official Resource Integration: The workflow involves retrieving a reference implementation from the official Microsoft GitHub organization. This ensures that the codebase originates from a trusted source for development and experimentation.
  • Developer Workflow Guidance: Operational notes provide clear instructions for using industry-standard tools like Vite and Yarn. It emphasizes user-driven execution and provides guidance on secure port configuration and environment isolation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 21, 2026, 04:03 PM
Security Audit — agent-trust-hub — msresearch-promptions