ClawHub

figma-pixel

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Figma visual QA skill whose token use, browser rendering, local artifacts, and frontend edits fit its stated purpose.

Install only if you are comfortable providing a read-scoped Figma token, running local browser/image comparison scripts, and letting the agent edit frontend files. Review code diffs before committing, check any added external font/CDN links, trust or clear module override environment variables, and clean up figma-pixel-runs when screenshots or Figma exports contain sensitive work.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill instructs the agent to automatically add third-party font provider links without user consent. That can change outbound network behavior, leak page access metadata to external CDNs, and introduce compliance/privacy issues in environments that prohibit unsolicited third-party dependencies or require self-hosted assets.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The code allows PLAYWRIGHT_MODULE_PATH from the environment to control what module is loaded via require(). In Node.js, requiring attacker-controlled paths can execute arbitrary code at load time, so a compromised or untrusted environment can turn this into code execution within the skill process. In this skill context, which drives a browser against user-supplied pages, that increases risk because the process likely has filesystem and network access needed for automation workflows.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal