troubleshoot-kubernetes-kube-proxy
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a legitimate troubleshooting guide for Netdata users. It instructs the agent to use established MCP tools (like list_nodes, query_metrics, and find_anomalous_metrics) to gather health signals for Kubernetes kube-proxy.- [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Netdata metric queries. While this represents a data ingestion surface, the risk is negligible as the data consists of numerical metrics and status codes used for diagnostic reasoning, and no high-privilege capabilities or command-execution tools are exposed to the resulting context.
Audit Metadata