Security audit
Security checks for vulnerabilities and agentic risk
This is a small OpenClaw monitoring helper whose code only checks local status and lists cron jobs, with no evidence of hidden installation, exfiltration, or destructive behavior.
Before installing, treat it as a read-only monitoring helper. If you enable any future Feishu or chat notification behavior, confirm the recipient, endpoint, and exact status data being sent, especially cron names or task details.
The entire skill description is presented in Chinese and brands the assistant interaction around Chinese-language messaging, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern.
The skill explicitly describes proactive status pushes to Feishu or chat windows but provides no notice about what data may be transmitted, who receives it, or whether user consent/configuration is required. In an agent/monitoring context, status messages can easily include task metadata, system health details, file names, or other sensitive operational information, creating a real privacy and data-leakage risk if sent externally by default.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
def list_jobs():
try:
result = subprocess.run(["openclaw", "cron", "list"], capture_output=True, text=True, timeout=10)
return result.stdout
except Exception as e:
return f"Error listing jobs: {str(e)}"
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
def check_gateway_status():
try:
result = subprocess.run(["openclaw", "gateway", "status"], capture_output=True, text=True, timeout=5)
if "running" in result.stdout.lower():
return "🟢 Gateway is Running"
return "🔴 Gateway is NOT Running"
The markdown states that the skill will proactively push status cards via Feishu or chat windows, which implies transmitting task or system-status information to external messaging surfaces. The description does not include any user-facing warning about what data may be sent, when notifications occur, or any privacy considerations.
SQP-3 applies to all file types and includes language or locale policy violations. The document consistently presents the skill in Chinese with no indication that users can choose another language or that the Chinese-only presentation is a documented, justified locale constraint.
No suspicious patterns detected.