The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of prometheus-mcp-server from PyPI, with source code hosted on a third-party GitHub repository (github.com/pab1it0/prometheus-mcp-server).
[INDIRECT_PROMPT_INJECTION]: The skill processes externally-sourced metric names, labels, and values from Prometheus servers, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The outputs of execute_query, execute_range_query, list_metrics, get_metric_metadata, and get_targets tools.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within metric data.
Capability inventory: The skill is restricted to read-only Prometheus operations (queries and discovery), limiting the impact of potential injection.
Sanitization: No explicit sanitization or validation of the retrieved Prometheus data is specified.
[COMMAND_EXECUTION]: The installation instructions utilize pip3 install to deploy the necessary MCP server component.

prometheus-monitoring