helm

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

• Third-party content exposure detected (high risk: 0.90). Yes — the SKILL.md explicitly instructs adding and installing charts from public chart repositories (e.g., "helm repo add bitnami https://charts.bitnami.com/bitnami" and using "helm search hub" / Artifact Hub), which causes the agent to fetch and render untrusted third‑party chart content that can influence deployments and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill includes runtime helm commands that fetch and install charts from external repositories (e.g. https://charts.bitnami.com/bitnami and https://charts.helm.sh/stable), which will retrieve remote manifests that are executed in the cluster, so these URLs constitute runtime external dependencies that can execute remote code.