ClawHub
Back to skill

Security audit

superguard

Security checks across malware telemetry and agentic risk

Overview

This skill is a plausible security integration, but it installs a high-privilege guard plugin that automatically provisions and stores credentials, sends security telemetry to a remote Core service, and may expose API keys without enough user control or disclosure.

Review before installing. Use this only if you trust OpenGuardrails and the MoltGuard plugin with security telemetry and local OpenClaw configuration changes. Treat the displayed API key as a secret, inspect the installed plugin/scripts before running enrollment or uninstall commands, and consider using a separate account or test environment first.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documentation states that an API key will be automatically obtained from a remote service and saved under the user's home directory without clearly warning the user that sensitive credentials are being provisioned and persisted locally. In a security-themed skill, this is especially risky because users may trust it more readily, while the docs also expose related commands that display API keys, increasing the chance of accidental disclosure or unsafe account linking.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.