gcloud

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gcloud command-line tool to query GCP project metadata, IAM configurations, and resource lists.
  • [DATA_EXFILTRATION]: Includes a command to access secrets stored in GCP Secret Manager (gcloud secrets versions access). While presented as an example for security validation, this provides a mechanism for the agent to retrieve sensitive credentials if authorized.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 01:57 AM
Security Audit — agent-trust-hub — gcloud