agent-platform-deploy

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various gcloud CLI commands to manage cloud infrastructure, including ai model-garden models deploy, ai endpoints create, and projects add-iam-policy-binding.
  • [COMMAND_EXECUTION]: Utilizes a local script scripts/config_gcloud_cli.sh to configure environment-specific gcloud profiles, including overriding the AI Platform API endpoint to a Google-owned sandbox domain (sandbox.googleapis.com).
  • [COMMAND_EXECUTION]: References an absolute file system path to an internal utility (/google/bin/releases/oneplatform/chemist/project_id_number_translator) for project ID translation, indicating the skill is designed for a specific internal development environment.
  • [COMMAND_EXECUTION]: Uses curl to interact with Google Cloud APIs, passing authentication tokens via $(gcloud auth print-access-token) to perform operations like model copying and prediction verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:03 AM
Security Audit — agent-trust-hub — agent-platform-deploy