ClawHub
Back to skill

Security audit

Css Free

Security checks across malware telemetry and agentic risk

Overview

This CSS helper is mostly documentation, but it asks for command execution, file writing, callback URL, and API key handling without explaining why those powers are needed.

Review this before installing. It may be fine if you intentionally want an agent to edit project files or run CSS-related tooling, but the skill does not explain those actions clearly. Prefer installing only if you can restrict command execution, file writes, callbacks, and API key exposure to trusted projects.

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 (1)

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill advertises `exec`, `write`, and a `callback_url` input despite presenting itself as a CSS helper, and it does not clearly warn users that it may execute commands, modify files, or send outbound notifications. This creates a capability/context mismatch that can mislead users into granting powerful actions under the assumption the skill is only generating CSS, increasing the risk of unintended code execution, file tampering, or data exfiltration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.