webapp-testing

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for this skill instructs the agent to navigate to a (local) webapp and then read/render page content/DOM via Playwright (e.g., page.content() / DOM inspection after page.wait_for_load_state('networkidle')), so any outsider-authored text that can appear in the webapp will be ingested by the LLM at runtime.