The Agent Skills Directory

[SAFE]: The skill operates by instructing the agent to query system metrics and diagnostic information through established Netdata MCP tools (e.g., list_metrics, query_metrics, find_anomalous_metrics). These tools provide a controlled interface for observability data.
[SAFE]: All diagnostic commands referenced in the rule files (such as lvs, vgs, pvs, and vgck) are standard Linux system administration tools. The skill uses these as context for explaining how Netdata's collector gathers data, rather than requiring the agent to execute arbitrary shell commands.
[SAFE]: No patterns indicative of data exfiltration, remote code execution, or unauthorized privilege escalation were detected. The skill's focus is restricted to infrastructure monitoring and remediation guidance within the scope of LVM management.
[SAFE]: Indirect prompt injection risk is negligible as the skill processes structured metric data and alert states from a trusted monitoring provider.

troubleshoot-lvm