browser-automation

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md describes Playwright/Puppeteer browser automation patterns (e.g., page.goto, extracting page content with page.content/textContent/response.json), but it does not define any runtime workflow that reads outsider-authored free text without the user first selecting specific targets.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly recommends disabling browser sandbox flags (--no-sandbox, --disable-setuid-sandbox) and hiding automation indicators (overriding navigator.webdriver / disabling automation features), which encourages bypassing security mechanisms on the host environment.