design-pro

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill's scripts deliberately load environment files and API keys and send local assets (logo images) and prompt text to an external Gemini/Google GenAI service, creating a clear data-exfiltration risk if users' secrets or private assets are uploaded unintentionally.

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

• Third-party content exposure detected (medium risk: 0.30). In the built-in “Banner: Workflow” (SKILL.md), the agent is instructed to “Research — Activate ui-ux-pro-max, browse Pinterest for references,” meaning outsider-authored free text from Pinterest pages/comments could be ingested without selecting a specific trusted item first.