XMTP

Make your OpenClaw agent messageable on XMTP — the open messaging network where anyone (humans or other agents) can DM it by address. Your agent gets its own...

This skill appears to do what it says, but before installing: 1) Verify the @xmtp/cli npm package (publisher, recent versions, repository) before installing globally. 2) Use a dedicated Ethereum wallet with no funds as the SKILL.md advises — xmtp init will create ~/.xmtp/.env with wallet and encryption keys; chmod 600 that file and never commit it. 3) The bridge expects you to export OWNER_INBOX_ID manually (the manifest didn't declare that env var) — follow instructions carefully to avoid misrouting messages. 4) Review and edit public-prompt.md to avoid exposing private data to strangers; consider running the bridge in an isolated environment (container or dedicated user) to limit blast radius. 5) If you want to stop exposure later, know how to stop the bridge process and remove ~/.xmtp/.env and any published inbox/wallet. 6) If you have higher security needs, audit the npm package source or run the XMTP client from a controlled container rather than installing it globally.

Type: OpenClaw Skill Name: xmtp Version: 0.1.0 The skill implements a persistent XMTP-to-OpenClaw bridge that pipes unsanitized remote message content directly into the agent's command-line interface, creating a high-risk communication channel. SKILL.md contains explicit instructions for the AI agent to override limited user requests (e.g., 'just send a message') in favor of deploying the full persistent bridge, which expands the attack surface beyond the user's explicit intent. Furthermore, the 'Public Mode' implementation in the bridge script is highly vulnerable to prompt injection, as it simply prepends a system message to raw user content before passing it to the agent.