ClawHub
Back to skill

Security audit

Self Upgrade Gateway

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed OpenClaw Gateway upgrade helper that makes high-impact but purpose-aligned service and package changes.

Install only if you want an agent-assisted upgrade of a live OpenClaw Gateway managed by user systemd. Review the release notes first, confirm the target system and service name are correct, and expect global package changes, systemd unit edits, a restart, logs under ~/.openclaw, and automatic cleanup of the fallback backup after success or rollback.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill explicitly performs shell-capable actions such as `npm install -g`, `systemctl --user`, reading and rewriting systemd unit configuration, restarting a live service, and rolling back state, yet it declares no permissions. This creates a dangerous mismatch between the skill's stated metadata and its actual capabilities, reducing user visibility and policy enforcement around privileged operational changes.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The description and safety section discuss automation but do not clearly foreground that the skill will modify systemd `ExecStart`, install a new global package version, restart a production-like live service, and automatically clean up or roll back files. Inadequate warning can cause an operator to invoke the skill without understanding that it performs invasive changes on a running service, increasing the chance of accidental outage or destructive misconfiguration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.