agent-platform-migrate-from-ai-studio

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the user to execute a setup script for Application Default Credentials (ADC) from Google's official cloud storage using bash process substitution.
  • Evidence: bash <(curl -sSL https://storage.googleapis.com/cloud-samples-data/adc/setup_adc.sh) in SKILL.md.
  • [COMMAND_EXECUTION]: The skill uses various standard gcloud CLI commands to facilitate project configuration, IAM policy management, and user authentication.
  • Evidence: gcloud services enable, gcloud auth login, and gcloud projects add-iam-policy-binding in SKILL.md.
  • [PROMPT_INJECTION]: The skill contains specific operational instructions for the AI agent, directing it to verify organization policy enforcement and interact with the user if constraints are detected.
  • Evidence: 'To the agent: Check if this policy is enforced, and if it is: pause, and prompt the user to disable it at this Console link' in SKILL.md.
  • [SAFE]: All remote references, including scripts and documentation, target well-known and trusted infrastructure associated with Google Cloud and official agent development tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:40 AM
Security Audit — agent-trust-hub — agent-platform-migrate-from-ai-studio