oxylabs-unblocking-browser

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly loads and interacts with arbitrary public websites using a remote headless browser (see SKILL.md and examples.md where page.goto(...) is used and page.content()/data extraction, form filling, and clicks are performed on external URLs like "https://example.com" and "https://example.com/products"), so untrusted third‑party content is ingested and can influence subsequent actions.