grafana

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime LLM context is fed by Grafana API responses (e.g., /api/search, /api/dashboards/uid/:uid, /api/v1/provisioning/alert-rules*, /api/ds/query), which are outsider-authored free text originating from the Grafana instance’s stored dashboard/alert content rather than the operating user.