new-service-deployment

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs adding and using public Helm/chart repositories (see Path A's "helm repo add" and templates.md helm repo examples and the Application sources[0].repoURL) and tells the operator to inspect chart values/service names and ports from those external charts (e.g., "inspect values" / "helm template"), meaning untrusted third-party chart content would be fetched and interpreted to decide ingress, service names, and Argo CD configuration and could therefore influence next actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill includes runtime fetches of external deployment artifacts (e.g., Helm/chart repos such as https://helm.goharbor.io and https://raw.githubusercontent.com/DefectDojo/django-DefectDojo/helm-charts, and the Argo CD git source https://github.com/tanut-pen/dev-sec-ops.git) that are pulled during install/sync and result in execution of remote manifests/charts which the workflow relies on.