start-new-sdk-project

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 arbitrary HTTP(S) URLs in the "Schema Sources" section (e.g., -s "https://api.example.com/openapi.json") and the agent will fetch and parse those external specs to generate SDKs, exposing it to untrusted third-party content that could carry indirect prompt-injection.