qe-compatibility-testing

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Agent-Driven Compatibility Testing" snippet (Task(..., { url: 'https://example.com', ... })) together with Playwright examples that call page.goto(...) show the agent will navigate to and ingest arbitrary target webpages, so it reads untrusted third‑party content which can influence testing actions and decisions.