branding

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs ingesting user/third-party-generated SVGs from AI generators (Phase 2: "Once you have the SVG, read it to understand its structure") and fetching public assets (e.g., downloading Google Fonts from raw.githubusercontent.com and loading Google Fonts CDN), and then parses and acts on those files (color extraction, text-to-path conversion, color replacement, asset generation), so untrusted external content directly influences tooling and decisions.