localization-testing

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

• Third-party content exposure detected (high risk: 0.90). The skill's tests and "Agent-Driven Localization Testing" task instruct agents to navigate to and inspect web pages (e.g., Playwright page.goto('/?lang=fr') and the Task url parameter like 'https://example.com'), which means the agent will fetch and read content from arbitrary target websites provided at runtime.