Citrea Claw Skill
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
When you ask Citrea-related questions, the agent may run the provided local CLI and show its output.
The skill explicitly asks the agent to execute local Node commands. This is expected for a CLI skill, but it means installation grants the agent command-running authority for the listed workflows.
immediately run the appropriate command below using the exec tool ... cd ~/.openclaw/skills/citrea-claw-skill && node index.js <command> [args]
Install only if you are comfortable with the agent running this Node CLI, and keep use to the documented commands and arguments.
A Telegram bot token could be used to send messages through your bot if exposed or mishandled.
The skill asks for a Telegram bot token and chat ID and stores them in the skill's .env file. This is purpose-aligned for alerts, but the bot token is a credential.
Telegram Bot Token ... write to `TELEGRAM_BOT_TOKEN` ... Telegram Chat ID ... write to `TELEGRAM_CHAT_ID`
Use a dedicated Telegram bot for this skill, keep the .env file private, and rotate the token if it is shared or exposed.
If the remote repository or dependencies change, the installed code may differ from the reviewed artifacts.
First-time setup pulls code and dependencies from remote sources. This is a normal installation path for a Node CLI, but it depends on the repository and npm dependency provenance.
git clone https://github.com/jason-chew/citrea-claw-skill.git ~/.openclaw/skills/citrea-claw-skill ... npm install
Verify the repository and package-lock before installing, and prefer pinned or reviewed versions when possible.
Monitoring alerts are sent to the configured Telegram chat, so the chat destination should be one you control.
The pool monitor sends alert messages to Telegram. This is disclosed and expected, but it is an external messaging boundary controlled by the configured bot token and chat ID.
await sendTelegram(`<pre>${msg}</pre>`)Confirm the Telegram chat ID before enabling alerts and avoid using shared chats unless you intend to disclose the alert contents there.
If enabled, the monitors can keep running in the background and continue sending alerts until stopped.
The setup guide documents optional always-on monitors that can persist across crashes and reboots. This is consistent with a monitoring skill, but users should intentionally enable and manage it.
PM2 ... keeps your scripts running forever and restarts them automatically if they crash ... pm2 save ... pm2 startup
Only enable PM2 monitoring when you want 24/7 alerts, and use pm2 status, stop, or delete commands to manage or remove the processes.