mockup-device-3d

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires embedding the user's real data/HTML verbatim into the generated screen HTML (no placeholders), which forces the model to output any secrets the user supplies and thus creates an exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 0.80). The page loads and executes remote JavaScript from https://cdn.tailwindcss.com at runtime (via ), and the skill's HTML relies on Tailwind classes for correct rendering, so this external script executes remote code and is a required runtime dependency.