Security audit
Security checks across malware telemetry and agentic risk
The skill is coherent and not malicious, but it gives Telegram chat commands high-impact control over skill installation and scheduled agent jobs without enough built-in safeguards.
Install only in a tightly controlled private setup. Before using it for real operations, add enforcement of Telegram chat.id and from.id in the executable path, restrict allowed skill publishers or slugs, require human approval for installs and cron changes, default new cron jobs to disabled or expiring, and keep the Dev bot token in protected configuration.
# Use openclaw cron add via stdin json (if supported) else via temp file.
# We'll write a temp file.
tmp = os.path.join(ws, "tmp-cron-job.json")
with open(tmp, "w", encoding="utf-8") as f:
json.dump(job, f)
rc, out = run(["openclaw", "cron", "add", "--file", tmp], cwd=ws)
try:65/65 vendors flagged this skill as clean.
No suspicious patterns detected.