google-cloud-scc-query

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Command Execution Patterns]: The skill provides templates for gcloud scc commands. These are restricted to read-only queries (list, group) and environmental configuration (gcloud config set api_endpoint_overrides). The skill explicitly prohibits modifying resources, applying patches, or executing configurations.
  • [Scope and Governance]: It implements 'Core Execution Rules' that mandate explicit parent scopes (projects/folders/organizations) and prohibits local credential searching or brute-force attempts. This ensures the agent operates under the principle of least privilege and does not attempt to escalate permissions.
  • [Instructional Guardrails]: The skill contains specific guidance to halt on PERMISSION_DENIED errors and avoid querying underlying resources (like VMs or Service Accounts) directly, focusing only on the SCC finding data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 12:15 AM
Security Audit — agent-trust-hub — google-cloud-scc-query