design-md-generator

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches arbitrary web pages and CSS via user-provided URLs using an extraction script (scripts/extract_css.py), ingesting external web content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill provides a helper script that fetches arbitrary user-supplied URLs at runtime to extract design tokens, introducing an unverifiable runtime external dependency under weak provenance.