ClawHub
Back to skill

Security audit

Vertical Font Conversion （CHINESE）

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local font-conversion workflow that reads user-provided fonts and writes local preview/test/output files without network, credential, persistence, or hidden install behavior.

Install only if you are comfortable running local Python scripts on font files you choose. Use a normal project/output directory, verify you have rights to convert the source font, and review generated previews before using the final TTF.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill explicitly directs use of local scripts that read source fonts, write output artifacts, and invoke Python entry points, which implies file read/write and shell-like execution capabilities despite having no declared permissions. This is dangerous because an agent or platform may grant broader access than users expect, reducing transparency and making it easier for a compromised or modified skill implementation to access arbitrary local files or execute unintended commands.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.