gcp-gke
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous CLI commands using
gcloudandkubectlfor infrastructure management. - Evidence: Commands for enabling APIs, installing components, creating clusters, managing node pools, and configuring IAM roles are documented throughout
SKILL.md. - Context: These operations are essential for the skill's stated purpose of managing Kubernetes clusters.
- [INDIRECT_PROMPT_INJECTION]: The skill contains multiple templates that interpolate user-provided variables, which represents a potential injection surface if the inputs are sourced from untrusted data.
- Ingestion points: Variable interpolation in shell scripts and Terraform configurations (e.g.,
${PROJECT_ID}, namespace names, and cluster names inSKILL.md). - Boundary markers: None identified in the provided templates.
- Capability inventory: The skill possesses significant capabilities including cluster creation, IAM policy modification, and workload deployment across
SKILL.md. - Sanitization: No explicit sanitization or validation of the interpolated variables is provided in the templates.
Audit Metadata