webapp-testing

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow uses Playwright to load and execute a specified web page (e.g., via page.goto(...) and page.content()), so if an outsider can cause the workflow to navigate to attacker-authored HTML/text, that text becomes LLM-readable at runtime.