claudecodeui-web-interface

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running npx to fetch-and-execute remote packages at runtime (e.g., "npx @cloudcli-ai/cloudcli" and MCP packages like "@modelcontextprotocol/server-filesystem") and supports installing plugins from git URLs (e.g., https://github.com/cloudcli-ai/cloudcli-plugin-starter), so external code is fetched and executed during runtime.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill documentation includes explicit commands that require elevated privileges (e.g., "sudo ufw allow 3001/tcp"), shows editing system-level configs (nginx /etc paths), and encourages enabling execute/write command tools and PM2 auto-start—actions that can modify system state and require or prompt use of sudo.