agents-get-started

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • Command Execution via Bash: The skill uses the Bash tool to interact with the agentcore CLI for essential tasks such as project initialization, local server management, and deployment. These operations are restricted to the skill's intended purpose. Crucially, the instructions mandate that the agent must present generated commands for user confirmation rather than executing them automatically, which provides a strong security boundary.
  • External Dependency Management: The skill includes instructions to install the @aws/agentcore package from the official NPM registry. This is a standard practice for installing developer tools from a well-known and reputable service.
  • Project Configuration Access: The skill reads local project files like agentcore.json and .env.local to understand the project structure and environment. Accessing these files is necessary for providing context-aware guidance during the development lifecycle.
  • Input Validation: The skill includes logic to validate user-provided project names (e.g., length and character restrictions) before incorporating them into commands, which helps prevent errors and ensures compatibility with underlying AWS services.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 02:58 AM
Security Audit — agent-trust-hub — agents-get-started