local-eks-development

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt embeds literal secrets and passwords in configs and scripts (e.g., KEYCLOAK_ADMIN_PASSWORD=admin, POSTGRES_PASSWORD=keycloak, clientSecret/local-dev-secret, aws --secret-string "local-dev-secret"), and includes commands that pass these values verbatim, so an agent following it would need to handle/output secret values directly.

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

• Third-party content exposure detected (high risk: 0.80). The skill's required setup script (scripts/dev-up.sh) runs kubectl apply -f https://raw.githubusercontent.com/kubernetes/ingress-nginx/main/deploy/static/provider/kind/deploy.yaml which fetches and applies a public GitHub manifest (third‑party, user-hosted content) as part of the core workflow, so untrusted remote content can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The setup script runs kubectl apply -f https://raw.githubusercontent.com/kubernetes/ingress-nginx/main/deploy/static/provider/kind/deploy.yaml at runtime, which fetches and applies remote Kubernetes manifests (executing remote configuration/code) as a required dependency.