functions

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow includes navigating to and scraping arbitrary, user-provided URLs (e.g., the "Parameterized Scraping" example and the dev/test invocation that call page.goto(params.url) and the curl example using "https://news.ycombinator.com"), which means untrusted third‑party web content is ingested and its content could influence subsequent results and actions.