Token Budget Monitor

Track and control token consumption across OpenClaw cron jobs

This skill appears to do what it says: it reads config.json in the skill folder and writes a local usage file to ~/.openclaw/workspace/outputs/token-usage.json. It asks for no credentials and makes no network calls. Before installing: 1) Review and, if desired, change the OUTPUT_DIR path to a location you control and ensure appropriate file permissions. 2) Do not paste untrusted values into the integration command as shown; avoid building shell commands by concatenation. Instead invoke the script with a safe argument array (child_process.spawn or execFile) or validate/sanitize job and model names to prevent command injection. 3) If you plan to run this under different users or CI, verify how HOME is set (code falls back to /home/ubuntu). 4) Run it in a sandbox or test environment first to confirm it writes only the expected JSON file. Overall this skill is internally consistent and low-risk for typical usage.

Type: OpenClaw Skill Name: token-budget-monitor Version: 1.0.0 The SKILL.md file contains an 'Integration' example that demonstrates a shell injection vulnerability. The `exec` call constructs a shell command by directly concatenating potentially untrusted inputs (`<job-name>` and `model`) without proper sanitization. This flaw could allow an attacker to execute arbitrary commands on the host system if they can control these input parameters, for example, through a malicious LLM response. This is a critical vulnerability, but there is no clear evidence of intentional malicious behavior (e.g., data exfiltration, backdoors) within the provided code or instructions, thus classifying it as suspicious rather than malicious.