google-cloud-solution-guided-gke-ai-migration

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs the agent to fetch and read external documentation at runtime (e.g., https://docs.cloud.google.com/kubernetes-engine/docs/concepts/about-gke-inference-gateway.md.txt and other supporting docs) to drive manifest generation and architectural decisions, meaning those remote URLs directly influence agent prompts/behavior and are required for correct operation.