ClawHub
Back to skill

Security audit

Cron Setup

Security checks across malware telemetry and agentic risk

Overview

The skill appears to set up scheduled automation, but it gives persistent command-execution authority through externally routed cron messages without enough scoping or user-control detail.

Install only if you understand and control the cron agent and Telegram destination. Treat any scheduled payload as code execution: review every command, avoid secrets or private workspace data in messages, and prefer user-configured channel IDs plus explicit approval before enabling recurring jobs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs cron jobs to send messages to a hard-coded Telegram channel and topic IDs, but it provides no warning, consent checkpoint, or data-handling limits. In a scheduled autonomous context, this creates a real risk of unintended external data transmission, including workspace details, alerts, or sensitive outputs being posted outside the local environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.