helm-validator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and uses external public content: Stage 6 falls back to a web.search_query (web search) to retrieve CRD documentation for manual validation, and Stage 7 instructs kubeconform to load JSON schemas from a raw.githubusercontent.com URL — both untrusted public sources whose contents are parsed and used to drive validation decisions.