ClawHub
Back to skill

Security audit

Auto Updater

Security checks across malware telemetry and agentic risk

Overview

The skill is openly an auto-updater, but it sets persistent daily automation that can change the agent and all installed skills without strong confirmation, scoping, or rollback guidance.

Install only if you deliberately want unattended daily updates for Clawdbot and all installed skills. Review or narrow the trigger keywords, require explicit confirmation before creating the cron job, and make sure you have a way to disable the job and recover from a broken update.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

High
Confidence
91% confidence
Finding
The trigger keywords are very broad (for example, 'auto', 'update', 'installed', and 'skills'), which increases the chance the skill activates during ordinary conversations unrelated to system maintenance. In this skill's context, accidental activation is more dangerous because the skill has exec capability and is designed to configure recurring update automation, potentially causing unintended system changes.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to set up a daily cron job and run package-management/update commands that modify the local environment, but it does not prominently warn about the operational impact, privilege requirements, or risks of unattended updates. In context, this is especially sensitive because it combines automatic scheduling with command execution and software updates from external sources, which can break environments or introduce supply-chain risk without clear user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.