OpenClaw Watch Dog

Self-healing monitoring system for OpenClaw gateway. Auto-detects failures, fixes crashes, and sends Telegram alerts.

This skill appears to do what it says: monitor OpenClaw locally and notify your Telegram bot. Before installing: 1) inspect the included scripts yourself or run them inside a controlled environment; 2) do not paste unrelated secrets into the chat — only provide the Telegram token/chat ID that you intend to use for alerts; 3) be aware the installer can optionally accept OpenAI/Anthropic keys and will store them encrypted locally if you provide them — only supply those if you understand why you need them; 4) the service can run npm install -g openclaw to reinstall the gateway, but it only does that after an explicit local approval file is created by you; 5) verify you trust the repository/source (homepage is provided) before granting persistent background execution. If you want higher assurance, run the setup steps manually rather than via an agent message.

Type: OpenClaw Skill Name: openclaw-watchdog Version: 1.3.0 The skill is designed for benign system monitoring and self-healing. However, the `scripts/setup.sh` file contains a critical shell injection vulnerability. When installing the systemd user service on Linux, the `printf` command used to generate the service file does not properly quote the `OPENCLAW_HEALTH_URL` environment variable. This variable is derived from the user-controlled `--gateway-port` argument. A malicious user could provide a crafted `GATEWAY_PORT` value (e.g., `8080; rm -rf /`) to inject arbitrary commands into the systemd service file, leading to Remote Code Execution (RCE) when the service starts. This vulnerability is exploitable via prompt injection against the AI agent, which is instructed to pass user-provided input to the `setup.sh` script.