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's --schema accepts HTTP(S) URLs (see "Schema Sources" e.g., https://api.example.com/openapi.json), and the agent ingests and interprets that OpenAPI spec to generate the SDK, exposing it to arbitrary untrusted third-party content that could carry indirect prompt injection.