google-cloud-recipe-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Command Execution]: The skill uses the
gcloudCLI to manage Google Cloud resources. This is the intended purpose of the skill. To ensure safe execution, it incorporates practices like appending--quietto prevent terminal hangs and using--format="json"for deterministic output processing. - [Consent and Authorization]: A strong security control is implemented where the agent must present a summary table and wait for explicit user confirmation before executing project creation or billing linkage commands. This prevents accidental resource deployment or financial charges.
- [Environment Auditing]: The skill performs non-interactive audits (e.g.,
gcloud auth list,gcloud projects list) to understand the current state of the environment before proposing changes, reducing the risk of redundant operations or errors. - [Usage Attribution]: The skill includes instructions to tag commands with a metrics environment variable (
CLOUDSDK_METRICS_REQUEST_ATTRIBUTION). This is a standard telemetry practice for identifying usage by specific automation tools and does not involve sensitive data exfiltration.
Audit Metadata