kubernetes-specialist

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a wide range of kubectl, helm, and shell commands intended for cluster administration. These include resource management, log inspection, and debugging operations like kubectl exec and kubectl debug to troubleshoot workloads.
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to download installation manifests and binaries for several standard Kubernetes utilities, including ArgoCD, Linkerd, and the Cluster API. All provided URLs point to the official GitHub repositories or project domains of these well-known services.
  • [REMOTE_CODE_EXECUTION]: Documentation for installing tools such as Istio and Submariner utilizes the curl | bash pattern. These scripts are sourced from official, well-known service domains as part of the standard installation process for these tools.
  • [PROMPT_INJECTION]: The skill processes external requirements for infrastructure design, creating an indirect prompt injection surface. * Ingestion points: Workload characteristics and security requirements defined in user prompts. * Boundary markers: The skill does not define specific boundary markers for untrusted input. * Capability inventory: Cluster management capabilities via kubectl and helm are described throughout the reference files. * Sanitization: The skill emphasizes security best practices but does not specify input sanitization mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 10:32 AM
Security Audit — agent-trust-hub — kubernetes-specialist