ClawHub
Back to skill

Security audit

plantuml-render

Security checks across malware telemetry and agentic risk

Overview

This is a small PlantUML rendering skill that creates diagram files and runs local Java rendering, with no evidence of hidden data access or destructive behavior.

Install only if you are comfortable running local Python and Java tools. Provide plantuml.jar from a trusted source, render files in a safe working directory, and avoid processing untrusted PlantUML content unless you have appropriate sandboxing.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill invokes shell-capable execution (`python ...` and `java -jar`) but does not declare permissions, which creates a transparency and governance gap. Even if the intended use is legitimate PlantUML rendering, undisclosed execution capability can lead users or orchestration systems to run local code without adequate review, increasing the chance of unsafe file handling or command misuse.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The skill instructs use of the write tool to create a PlantUML file without warning the user that files will be created or modified on disk. This is primarily a safety and consent issue: unexpected file creation can overwrite existing content, place files in sensitive locations, or surprise users in restricted environments.

VirusTotal

45/45 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.