generate-terraform-provider

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts OpenAPI specs from URLs (Inputs: "local file, URL, or registry source") and documents fetching remote specs/overlays (e.g., the "Remote spec with overlays" workflow using https://api.vendor.com/openapi.yaml and the speakeasy overlay compare command), so the agent will ingest and interpret arbitrary third-party OpenAPI documents from the public web, enabling indirect prompt injection risks.