qa-testing

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly requires "The page URL or site under test" and its SKILL.md instructs running console snippets (document.querySelector… scripts) and a fetch(window.location.origin, { method: 'HEAD' }) that read DOM and headers from arbitrary public sites, so untrusted third‑party page content is ingested and used to drive pass/fail decisions and next actions.