backend-go-observability

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly tells users/agents to "browse" and "copy" rules from the public awesome-prometheus-alerts site (references/alerting.md) and to install community Grafana dashboards from grafana.com (references/dashboards.md), which are open/public, third-party (often user-contributed) sources whose content the agent is expected to read and act on (e.g., copying alert rules and dashboards), so it exposes the agent to untrusted third-party content that can influence tooling and actions.