celigo

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires installing/running the Membrane CLI (npm install -g @membranehq/cli@latest — e.g. https://www.npmjs.com/package/@membranehq/cli), and the Membrane connection API can return clientAction.agentInstructions at runtime which directly supplies instructions for the AI agent, so remote content fetched/executed by this dependency can control prompts.