ClawHub
Back to skill

Security audit

Auto Updater.Bak2

Security checks across malware telemetry and agentic risk

Overview

The skill is upfront about being an auto-updater, but it gives a persistent daily job broad authority to change Clawdbot and every installed skill without per-update review.

Install only if you intentionally want automatic scheduled updates to the agent and every installed skill. Prefer a notify-only or dry-run setup, review updates before applying them, pin or allowlist critical skills where possible, and confirm you know how to remove the cron job before enabling it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly sets up unattended daily updates for both the core bot and all installed skills, which are write operations affecting executable tooling. Because the documentation does not prominently warn about supply-chain risk, unexpected breaking changes, or the need for user approval/change windows, it normalizes automatic modification of trusted software and increases the chance of compromised or unstable updates being applied silently.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
This guide instructs the agent to configure unattended daily updates for both Clawdbot and all installed skills, including running migrations via `clawdbot doctor --yes`, without requiring approval, pinning versions, or adding safety checks. That creates a supply-chain and operational risk: remote code and schema changes can be pulled and applied automatically, potentially breaking the system or introducing malicious updates with no human review.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.