security-visual-testing

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows and integration explicitly navigate to and analyze arbitrary public URLs (see SKILL.md "Security Visual Audit" CLI examples and the Integration section calling scanner.scanUrl('https://example.com')), ingesting page content (PII, security, accessibility) which the agent uses to make decisions and generate reports, so untrusted third-party content can materially influence behavior.