ClawHub
Back to skill

Security audit

diagram-generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed diagram-generation helper that writes diagram files and may initialize its diagram-tool configuration, with no evidence of hidden data access or unrelated behavior.

Install this if you want agents to create or edit diagram files. Be aware that it depends on the mcp-diagram-generator MCP server, may run it through npx if configured that way, and can create .diagram-config.json plus diagram output directories and files in the workspace.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill metadata says to 'Always use this skill when the user asks to draw, generate, revise, or export any diagram,' which is broad routing language that can cause the agent to invoke this file-writing skill more often than necessary. Because the skill can create directories, write files, and even instruct reconfiguration of an MCP server, over-invocation increases the chance of unintended filesystem changes or tool use without sufficiently narrow user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The output instructions tell the agent to provide a saved file path, while the skill as a whole also states that the MCP server creates missing directories and writes files by default, but there is no explicit user-facing warning that using the skill will modify the filesystem. In this context, that omission is risky because a user may expect advisory help but instead trigger file creation, directory creation, or configuration initialization.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.