aidesigner-frontend

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

• Third-party content exposure detected (low risk: 0.10). The skill uses an MCP server (api.aidesigner.ai) to generate UI designs from user prompts, local repo context, and optional reference URLs, without monitoring any outsider-authored feeds or untrusted external submission channels.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external remote MCP server and execution packages via npm, but lacks established official enterprise publisher provenance, resulting in a high-tier risk rating.