aidesigner-frontend

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly documents a generate_design 'url' parameter and "inspire/clone/enhance" modes and states "Reference-based design: Clone or get inspired by competitor sites", indicating the remote MCP (https://api.aidesigner.ai) will fetch and ingest arbitrary public web pages to drive generation, which could enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime calls to the remote MCP endpoint https://api.aidesigner.ai/api/v1/mcp which executes remote generation logic and injects repo context that directly controls prompts/results, so this external URL is a required runtime dependency that executes remote code.