model-serving-kubernetes

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill instructs runtime fetching and execution of external Helm charts and container images (e.g., helm repo https://kserve.github.io/helm-charts and images like nvcr.io/nvidia/tritonserver:24.05-py3, vllm/vllm-openai:latest, kserve/kserve-transformer:latest), which are pulled at runtime and will execute remote code in the cluster, creating a real supply-chain/execution risk.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 11:44 PM