ClawHub
Back to skill

Security audit

Style Guide Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent document-generation helper that analyzes user-provided design sources, with no included executable code or hidden persistence found.

Use this skill with public websites or materials you are authorized to process. Avoid providing internal URLs, confidential brand documents, or sensitive screenshots unless that analysis is appropriate in your workspace, and review the generated PDF before sharing it.

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

Low
Confidence
93% confidence
Finding
The skill instructs the agent to fetch and analyze live websites from user-provided URLs, but the description does not clearly warn users that external network access will occur. This can lead to unexpected requests to third-party or internal hosts, creating consent, privacy, and possible SSRF-style exposure concerns if users provide sensitive or untrusted URLs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.