ClawHub
Back to skill

Security audit

Plantuml

Security checks across malware telemetry and agentic risk

Overview

This is a PlantUML reference skill that helps an agent generate diagram text and does not show hidden, persistent, or privileged behavior.

Install this if you want your agent to produce PlantUML diagrams. When rendering diagrams with external includes or an online PlantUML server, avoid sending confidential architecture, schema, or business data unless that rendering path is acceptable for your environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The README suggests very broad natural-language activation phrases like 'draw a login sequence diagram' or 'draw a C4 container diagram for this microservice system' without documenting boundaries, required confirmation, or trigger conditions. In agent environments, overly generic examples can cause the skill to activate on routine user requests and steer the agent into using this skill unexpectedly, increasing the chance of incorrect tool selection, overreach, or unintended processing of supplied content.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.