Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/clickhouse-observability/Gen Agent Trust Hub

clickhouse-observability

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and downloads configuration from well-known technology services.
  • Targets ClickHouse Cloud's official Prometheus endpoint at api.clickhouse.cloud.
  • References an official community dashboard hosted on Grafana's public repository (grafana.com/grafana/dashboards/23415).
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting data from ClickHouse system tables which may contain untrusted content.
  • Ingestion points: The skill reads from system.query_log and system.processes, which store the text of queries executed on the server (references/system-tables.md).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent for handling potentially malicious strings embedded in query logs.
  • Capability inventory: The skill uses Read, Write, and Edit tools to generate configuration artifacts like prometheus.yml and clickhouse-alerts.yml.
  • Sanitization: The skill provides templates for structured monitoring but does not implement specific sanitization for the content of the logs it queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:45 AM