k8s

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Researching Unfamiliar Services" workflow explicitly directs spawning a subagent to research external documentation starting with third‑party docs URLs (e.g., cert-manager.io, longhorn.io, grafana.com, prometheus.io), meaning the agent will fetch and interpret public web content that can influence troubleshooting actions.