ClawHub

Figma

Security checks across malware telemetry and agentic risk

Overview

This Figma skill is mostly coherent, but its setup instructions include running remote installer scripts directly in a shell.

Use this only if you trust OOMOL with your connected Figma account. Install or update the `oo` CLI yourself from a verified source instead of letting an agent run the remote shell installer, and review every Figma write or delete payload before approving it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The file documents a read-only action (`list_comment_reactions`) as a write action that changes Figma state, which can mislead an agent or operator into applying the wrong safety posture. In an agent skill, inaccurate action semantics are security-relevant because they can cause unnecessary confirmation prompts, policy mismatches, or incorrect trust decisions about what an action does.

External Script Fetching

High
Category
Supply Chain
Content
- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):

  ```bash
  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  ```

  ```powershell
Confidence
97% confidence
Finding
curl -fsSL https://cli.oomol.com/install.sh | bash

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal