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: 0.90). The skill explicitly instructs the agent to fetch and read external reference documents at runtime (e.g., "Fetch About GKE Inference Gateway" at https://docs.cloud.google.com/kubernetes-engine/docs/concepts/about-gke-inference-gateway.md.txt), which means those remote URLs directly influence the agent's prompts/instructions during execution.