lettria

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires and invokes the Membrane CLI which the skill instructs to fetch and execute at runtime via "npm install -g @membranehq/cli@latest" / "npx @membranehq/cli@latest" (remote package from the npm registry, e.g. https://registry.npmjs.org/@membranehq/cli), so external code is fetched and executed and is required for the skill to operate.