fal-ai-media

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running an MCP via the command "npx -y fal-ai-mcp-server" (which fetches and executes the remote npm package, e.g. https://registry.npmjs.org/fal-ai-mcp-server) at runtime, so it pulls and runs external code that the skill depends on.