ClawHub

Openclaw Design Consult

Security checks across malware telemetry and agentic risk

Overview

This design-consulting skill is instruction-only and its project reads, optional web research, preview generation, and design-file updates are disclosed and aligned with its purpose.

Install this if you want an agent to help define a design system for a project. Expect it to read project context, optionally use web research, create a local preview, and modify DESIGN.md/CLAUDE.md; decline competitor research if you do not want browsing, and review generated file changes before committing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The skill frames itself as a generally conversational design consultant and explicitly says the user can "directly chat about anything," which weakens scope boundaries and makes accidental or inappropriate invocation more likely. Broad trigger language is risky because it can cause the agent to engage outside the intended design-consult domain, increasing the chance of unintended tool use or repository modifications in loosely related conversations.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to create a temporary HTML file and automatically open it in the browser without requiring user confirmation or warning that a local file will be written and executed in a browser context. Even though the content is intended as a design preview, automatic file creation and browser launch are side effects that can surprise users, expose local context in rendered output, and normalize unsafe autonomous behavior.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill directs the agent to write DESIGN.md and append to CLAUDE.md as part of normal operation, but it does not require an explicit warning or confirmation before modifying repository files. Silent or assumed file mutation is dangerous because users may invoke the skill for discussion or exploration and unintentionally end up with persistent changes to project guidance files that affect future agent behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal