kubernetes-operations

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

• Third-party content exposure detected (high risk: 0.90). This skill's documentation (REFERENCE.md and SKILL.md) includes commands that fetch and apply remote, public content—e.g., "kubectl create -f https://example.com/manifest.yaml", "helm repo add ...", and "curl https://raw.githubusercontent.com/... | bash"—which cause the agent/operator to ingest and act on untrusted third-party content that can change behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill includes a runtime installation command that fetches and executes remote code—"curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash"—which runs a script from GitHub to install Helm, a dependency used by the skill's Helm workflows.