Private Bridge

Secure outbound-only relay for remote OpenClaw control — no exposed ports, no SSH, no Telegram.

This skill appears internally consistent, but it gives a remote operator the ability to send prompts, trigger workflows, and restart your OpenClaw instance over an authenticated outbound channel. Before installing: only configure a relay URL you trust, treat AUTH_TOKEN like a secret and rotate it if compromised, review the relay operator's privacy/persistence guarantees (the client cannot enforce server-side retention), run the skill on a host with appropriate isolation/permissions, and monitor logs/network usage. If you need stronger assurance, review the relay server code or host your own relay.

Type: OpenClaw Skill Name: private-bridge Version: 1.0.2 The skill provides powerful remote control capabilities, including executing AI prompts, triggering workflows, and restarting the OpenClaw process, as defined by the `OpenClawRuntime` interface in `capabilities.ts` and implemented in `relayClient.ts`. While these capabilities are transparently declared in `SKILL.md` and `README.md` and align with the stated purpose of remote management, they inherently introduce a significant attack surface. If the remote relay server (e.g., `wss://relay-terminal-cloud.fly.dev`) is compromised, or if the host OpenClaw runtime's implementation of `executePrompt` or `executeWorkflow` is not adequately sandboxed, these declared functionalities could be exploited for remote code execution or unauthorized system manipulation. There is no evidence of intentional malicious behavior such as unauthorized data exfiltration, persistence mechanisms, or obfuscation within the skill's code or documentation.