kubernetes-specialist

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

• Third-party content exposure detected (high risk: 1.00). The REFERENCE.md workflow explicitly instructs fetching and applying public manifests (e.g., kubectl apply -f https://raw.githubusercontent.com/argoproj/argo-cd/stable/manifests/install.yaml and adding helm repos like https://prometheus-community.github.io/helm-charts), so the skill requires ingesting untrusted, user-hosted third-party content that can materially change actions and cluster state.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill includes explicit runtime commands that fetch and apply remote manifests/charts — for example "kubectl apply -n argocd -f https://raw.githubusercontent.com/argoproj/argo-cd/stable/manifests/install.yaml" and "helm repo add prometheus-community https://prometheus-community.github.io/helm-charts" — which download and execute remote configuration/code and are presented as required steps in the workflow.