py-async

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

• Third-party content exposure detected (high risk: 0.70). The skill's documentation (SKILL.md "Pattern 1: 並行 HTTP 請求（aiohttp）" and references/examples.md) contains code (e.g., fetch_all(urls), fetch_with_retry) that explicitly fetches and parses arbitrary public URLs (httpx/aiohttp session.get and .text/.json), meaning the agent would ingest untrusted third-party web content as part of its workflow.