Self-Integration

Connect to any external app and perform actions on it. Use when the user wants to interact with external services like Slack, Linear, HubSpot, Salesforce, Jira, GitHub, Google Sheets, or any other app — send messages, create tasks, sync data, manage contacts, or perform any API operation.

This skill delegates access to other apps through the Membrane service. Before installing, ensure you trust the Membrane service and only supply a token with the minimum scope needed (or a limited/test account) because the token lets the skill perform actions on connected apps. Understand that the agent will initiate connection flows that may require the user to open authentication URLs to grant access to external services. If you need stronger assurances, ask for details about token scope, audit logs, and how to revoke the token.

Type: OpenClaw Skill Name: self-integration Version: 1.1.2 The skill acts as a client for the Membrane API, enabling interaction with external applications. It requires `MEMBRANE_TOKEN` and `MEMBRANE_API_URL` environment variables, which are used to authenticate and direct all API calls to the specified Membrane endpoint (defaulting to `https://api.getmembrane.com`). The `SKILL.md` transparently outlines the API interactions, data sent (API token, connection parameters, action inputs, agent prompts), and explicitly states that no other external services are contacted. While the skill instructs the OpenClaw agent to send 'prompts' to the Membrane API's agent sessions, this is a documented feature of the Membrane service for building connectors/actions, not a prompt injection attempt against the OpenClaw agent itself. There is no evidence of unauthorized data exfiltration, malicious execution, persistence mechanisms, or obfuscation. The skill clearly discloses its reliance on and data sharing with the Membrane service, aligning with its stated purpose.