browser-use

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly navigates to and inspects arbitrary external http/https URLs (see SKILL.md "URL (http/https) → Reconnaissance-then-action" and examples like examples/basic_automation.py and examples/element_discovery.py which call page.goto(url) and page.content()/locator() to read and act on third‑party page content), so untrusted web content can be ingested and influence automation actions.