moai-workflow-testing

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

• Third-party content exposure detected (high risk: 0.80). The skill includes Playwright-based web testing that navigates to and screenshots arbitrary web pages and captures API responses (see modules/advanced-patterns.md: page.goto('https://example.com'), Visual Regression, APIInterceptor.recordAPITraffic and Lighthouse integration), which means the agent workflows fetch and ingest open/public third‑party content that could contain untrusted, user-generated input.