qe-visual-accessibility

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

• Third-party content exposure detected (high risk: 1.00). The skill's Agent Workflow and operation examples (e.g., responsiveTester.test({ url: 'https://example.com' }), accessibilityAgent.audit({ url: 'https://example.com' }), and visualTester.compareScreenshots using 'production'/'staging' sources) explicitly fetch and analyze arbitrary public web pages, meaning untrusted third-party content is ingested and can materially influence tests and subsequent actions.