wcag-audit-patterns

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Automated Testing" and "CLI tools" sections explicitly show running audits against web pages (e.g., page.goto('/') in the Playwright example and commands like "npx @axe-core/cli https://example.com" / lighthouse against URLs), so the skill fetches and interprets arbitrary public web content that could contain untrusted/user-generated instructions influencing audit decisions and follow-up actions.