google-cloud-slo-alert-configuration

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests user-provided free text via the structured wizard conversation (collecting ServiceScope/ServiceLevel/SLI/alerting inputs) and later uses those values to generate PromQL/Terraform, so outsider-authored text can directly influence what the agent processes.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's references/service_metrics.md explicitly requires using the read_url_content tool at runtime to fetch external documentation from https://docs.cloud.google.com/monitoring/docs/application-monitoring-services.md.txt, which would directly influence SLI/metric mappings and thus control agent behavior.