standard-out-setup

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

• Third-party content exposure detected (high risk: 0.80). The skill includes code examples that ingest untrusted third-party content—e.g., the API endpoint example upload_file(file: UploadFile) which processes user-uploaded files and the fetch_data() example that calls requests.get(url) to load arbitrary URLs—so an agent could read and act on external, user-generated/public web content.