kubernetes-specialist
Warn
Audited by Snyk on Feb 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill includes commands and workflows that fetch and ingest content from public, user-hosted sources (e.g., kubectl apply -f https://raw.githubusercontent.com/argoproj/argo-cd/stable/manifests/install.yaml, helm repos like https://charts.bitnami.com/bitnami, and various GitHub repo URLs), so the agent would read and act on untrusted third-party content.
Audit Metadata