Playwright Browser Automation

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

• Third-party content exposure detected (high risk: 0.90). The skill navigates to and fetches arbitrary external URLs (e.g., page.goto(TARGET_URL), the broken-links checker visiting link hrefs, helpers.extractTableData, and accepts user-provided or discovered URLs), so it clearly ingests untrusted public web content that the agent will read and interpret.