kubernetes-specialist

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required workflow instructs the agent to validate and troubleshoot by running kubectl commands such as kubectl describe pod <name> and kubectl logs <pod-name> --previous, which ingest attacker-controlled free text from Kubernetes resources like pod specs/status/messages and container log output at runtime.