python-async-patterns

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

• Third-party content exposure detected (high risk: 0.70). The skill includes multiple examples that fetch and process arbitrary external URLs (e.g., fetch_data(url: str), fetch_many_urls(urls: list[str]), and FastAPI endpoints using aiohttp to call external APIs like /external-data), which means an agent following these workflows could ingest untrusted, user-provided web content and be exposed to indirect prompt injection.