ClawHub
Back to skill

Security audit

style-extractor

Security checks across malware telemetry and agentic risk

Overview

This skill reads user-provided webpages, screenshots, or project style files to create a reusable design-token style skill, and its access is disclosed and aligned with that purpose.

Install only if you are comfortable letting the agent fetch user-provided webpages and inspect style-related files in projects you explicitly point it at. Avoid using private/internal URLs or repositories containing secrets unless you intend that content to be analyzed for design-token extraction.

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)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The README advertises automatic CSS fetching from URLs, which implies the skill may initiate outbound network access and retrieve remote content without clearly warning the user. In an agent context, this can lead to unexpected data transmission, requests to untrusted hosts, or SSRF-like misuse if users provide internal or sensitive URLs.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The README states that the skill can analyze frontend project source code, but it does not warn users that local files or repositories may be read and processed. In an agent environment, that can cause unintentional exposure of proprietary code, secrets embedded in repos, or broader workspace access than the user expects.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.