playwright

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime (SKILL.md workflow, examples like examples/link-checker.js, helpers.detectDevServers and lib/helpers.js functions such as extractTexts, extractTableData, handleCookieBanner, page.request.head, and run.js which executes inline code) navigates to and fetches arbitrary web pages and external links (including user-provided URLs and pages discovered on visited sites), so untrusted public content is read and acted on as part of normal automation flows.