ClawHub Auto Updater

Security checks across malware telemetry and agentic risk

Overview

This skill openly sets up daily automatic updates for Clawdbot and installed skills, which is useful but can change your agent environment without reviewing each update first.

Install this only if you want Clawdbot and all installed skills to update automatically from upstream sources. For critical setups, run the dry-run command first, pin or manually review important skills where possible, and know how to remove the cron job if automatic changes cause problems.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This skill explicitly sets up unattended daily updates for both the core bot and all installed skills, but it does not clearly warn users that third-party code and behavior may change automatically without prior review. That creates a meaningful supply-chain and stability risk: a bad or compromised upstream release could be pulled and applied automatically, potentially affecting all installed skills and the bot runtime.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The guide instructs the agent to set up unattended package and skill updates plus a recurring cron job, but it does not require explicit user acknowledgement of the ongoing autonomous changes this will cause. This is dangerous because it enables continuous modification of the bot and its installed skills, increasing the chance of unexpected breakage or supply-chain compromise without a fresh user approval at each change.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal