google-cloud-recipe-onboarding

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill utilizes the official Google Cloud CLI (gcloud) to perform project management and billing linkage. While these commands modify cloud resources, they are fundamental to the skill's purpose of onboarding a developer to the platform.
  • Input Handling Consideration: The skill accepts user input for parameters like project IDs and names, which are incorporated into shell commands. This is a common pattern for CLI-based skills; to address the potential for unintended command behavior, the skill requires a structured confirmation step and explicit user consent before proceeding with mutations.
  • Authentication and Scoping Safeguards: The skill includes robust checks to verify the user's authentication state and environment. Notably, it contains logic to detect if the user is part of an enterprise organization and halts execution to redirect them to official enterprise setup guides, ensuring the skill is used in the correct context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 07:52 PM
Security Audit — agent-trust-hub — google-cloud-recipe-onboarding