application-design-center-design-deploy

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md phase 1 calls the design skill for the user’s prompt, and the design skill ingests that free-text intent to drive catalog/module selection and generation; however it does not read arbitrary outsider-authored feed text without the user explicitly providing it as the prompt.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill mandates constructing Terraform module sources like "github.com/GoogleCloudPlatform/terraform-google-cloud-run//modules/v2?ref=v0.33.0" and running terraform init/plan during runtime, which will fetch and execute remote module code from that GitHub URL as a required dependency.