skills/rysweet/amplihack/aspire/Gen Agent Trust Hub

aspire

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and execute installation scripts for .NET Aspire and the Azure Developer CLI.
  • Fetches configuration and installation scripts from the official product domain aspire.dev and Microsoft's aka.ms service.
  • [COMMAND_EXECUTION]: Extensive use of CLI tools for project orchestration, deployment, and troubleshooting.
  • Instructs the agent/user to execute dotnet, aspire, azd, and docker commands to manage service lifecycles, resource topology, and infrastructure provisioning.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts on user-supplied requirements to architect and generate distributed application configurations, creating a potential vector for indirect instructions.
  • Ingestion points: User-provided microservice requirements and architecture descriptions processed during the orchestration setup (e.g., "Setup Aspire for microservices").
  • Boundary markers: None explicitly defined in the provided instruction text to separate user-provided requirements from agent instructions.
  • Capability inventory: The skill has access to file system writes (creating projects), command execution (dotnet, azd, aspire), and network operations for cloud deployment.
  • Sanitization: The documentation does not specify sanitization or validation routines for user-provided identifiers or configurations during the generation of AppHost code or CLI arguments.
  • [CREDENTIALS_UNSAFE]: The skill promotes secure secrets management practices throughout its documentation.
  • Recommends using dotnet user-secrets for local development and Azure Key Vault for production environments.
  • Explicitly warns against hardcoding secrets in source code and provides examples of managed identity usage to avoid password-based connection strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 04:52 PM