ClawHub
Back to skill

Security audit

OpenClaw Color Palette

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent remote color-design helper; the main caution is that image or color inputs are sent to its disclosed MCP service for processing.

Install this only if you are comfortable sending color values, image URLs, screenshots, logos, or base64 image data to the listed remote MCP service. Avoid sensitive or proprietary images unless you trust the provider and its no-storage claims.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are broad enough to activate on many normal design-related requests, which can cause the skill to be invoked when the user did not specifically intend to use this external capability. Over-broad activation increases the chance of unnecessary data being sent to the MCP endpoint and can create confused-deputy behavior where the agent prioritizes the skill over safer built-in handling.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.