ClawHub

Frontman — Visual Frontend Editing

Security checks across malware telemetry and agentic risk

Overview

This is a coherent visual frontend editing skill that can install Frontman and change project source files, with those capabilities disclosed and aligned to its purpose.

Install this only when you want Frontman-style visual editing in a version-controlled project. Invoke it explicitly, review package/config changes and diffs before keeping them, and store any OpenAI/Anthropic/OpenRouter keys in a proper environment variable or secret manager rather than pasting them into chat, source files, screenshots, or logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger list is broad enough that this skill may activate for many ordinary frontend-related requests, causing an agent to steer users into installing and using a powerful code-editing tool when they may not have asked for it. In this context, overbroad activation is more dangerous because the skill can invoke shell and browser tooling and ultimately lead to real source-file changes.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly states that Frontman edits actual source files, but it provides no requirement to warn the user, summarize pending changes, or obtain confirmation before modifying code. That is risky because a visually driven editing workflow can make unintended or unsafe changes feel low-friction, especially when paired with hot reload and agent-driven shell/browser actions.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill mentions bring-your-own API keys but gives no warning about secure handling, storage, scope, or exposure risks. In a tool that bridges browser context, server-side agents, and source editing, missing credential-safety guidance increases the chance that users paste secrets into unsafe places or expose them through logs, config files, or the UI.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal