grafana-mcp-tools

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

• Third-party content exposure detected (medium risk: 0.65). The skill is an MCP server that exposes Grafana API tools; at runtime the agent will ingest Grafana responses (e.g., dashboard JSON, alert rule text, log query results) which are outsider-authored content from the Grafana instance (not authored by the operating user), creating indirect prompt-injection risk via tool outputs.