ClawHub
Back to skill

Security audit

Openclaw Plugin

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for helping users build OpenClaw plugins, with credential and plugin-power risks disclosed enough to handle through normal caution.

Install this if you want help creating OpenClaw plugins. Review any generated plugin code and manifests before enabling them, keep side-effect tools optional or explicitly allowed, and store real API keys or bot tokens outside source-controlled files whenever possible.

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
91% confidence
Finding
The documentation shows an `openclaw.yml` example containing plaintext bot tokens directly in configuration without any nearby warning to use environment variables, secret stores, or redaction. In a plugin-creation skill, readers are likely to copy this example verbatim, which can lead to credentials being committed to source control, shared in chat, or exposed in logs and screenshots.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal