design-judge-skills

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves searching and navigating official award galleries and pages at runtime, which represents low-risk ingestion of external web content.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions direct the runtime execution of npx skills add SeanJ1ang/design-judge-skills from an unofficial GitHub repository locator, which fetches and installs agent skills and code.