gke-basics

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow includes applying manifests fetched directly from public third-party URLs (for example, references/gke-batch-hpc.md instructs "kubectl apply --server-side -f https://github.com/kubernetes-sigs/kueue/releases/latest/download/manifests.yaml" and "kubectl apply -f https://raw.githubusercontent.com/kubeflow/mpi-operator/..."), so it clearly ingests untrusted, user-maintained web content which the agent is expected to read/act on and which could materially influence subsequent tool actions.