azure-functions-deploy

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to install the Azure Skills plugin using an npx command pointing to a Microsoft-owned GitHub repository. This is an expected and safe operation for a deployment-focused tool from a trusted organization.
  • Evidence: npx skills add https://github.com/microsoft/azure-skills/tree/main/.github/plugins/azure-skills/skills -a github-copilot -g -y (SKILL.md)
  • [COMMAND_EXECUTION]: Provides standard Azure CLI and Azure Developer CLI commands for monitoring deployment progress, resource group status, and Function App health. These commands are diagnostic and operate within the user's authenticated session.
  • Evidence: az group show, az deployment group list, and az functionapp list (SKILL.md)
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by reading project configuration files to determine the deployment path.
  • Ingestion points: host.json, azure.yaml, and infrastructure files (Bicep/Terraform) in the project directory.
  • Boundary markers: Absent; the skill does not use specific delimiters when reading these configuration files.
  • Capability inventory: Invokes downstream deployment skills (azure-prepare, azure-validate, azure-deploy) and executes monitoring commands.
  • Sanitization: Absent; the skill relies on the delegated tools (azure-validate) to perform integrity checks on the deployment plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 12:47 AM
Security Audit — agent-trust-hub — azure-functions-deploy