browser-automation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly describes web-scraping and agentic browser control that navigates arbitrary URLs and extracts/acts on page content (e.g., scrapeProduct(page, url) using page.goto(url), parallel scraping examples, and stealth patterns), meaning the agent will fetch and interpret untrusted third‑party webpages as part of its workflow.