ClawHub

Openclaw Update

Security checks across malware telemetry and agentic risk

Overview

This is a transparent OpenClaw updater skill whose higher-impact commands are visible and aligned with its stated purpose.

Install this only if you want agent help managing OpenClaw updates. Before running update commands, confirm the package source and target version, expect a gateway restart to interrupt service, and schedule any cron-based checks deliberately.

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
93% confidence
Finding
The skill documents commands that modify a global OpenClaw installation and restart the gateway, but it does not clearly warn that these actions change system state and may interrupt running services. In an agent skill context, this is risky because a user or automation may execute the workflow without realizing it performs privileged package changes and a service restart.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly documents global update and gateway restart commands without warning that they change installed software and can interrupt a running service. In an agent context, this can lead to unreviewed self-updates, operational disruption, or pulling untrusted code if the update source is overridden or compromised.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal