anti-ui-slop

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

• Third-party content exposure detected (low risk: 0.10). The skill references UIZZE search tools (find_ui_references, find_ui_materials) which fetch optional design references and materials from uizze.com.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of external code via an npx command referencing an unverified third-party domain (uizze.com), introducing an operational dependency with weak provenance.