Back to skill

Security audit

Baoyu Diagram

Security checks across malware telemetry and agentic risk

Overview

This is mostly a diagram-making skill, but it needs review because it can create files and run Bun/npx conversion code despite describing the output as SVG-only.

Review before installing. Use it only in a workspace where generated diagram files are acceptable, check the intended output path first, and be aware that it may run Bun or `npx -y bun` to create a PNG in addition to the SVG.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

High
Confidence
85% confidence
Finding
The trigger conditions are extremely broad and can cause the skill to activate for many generic requests involving diagrams, uploaded content, or phrases like 'draw me a ...'. Over-broad activation increases the chance of unintended file generation, unexpected tool use, and processing of sensitive user-provided material without sufficiently explicit intent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs saving files and creating directories automatically, but does not require explicit user confirmation or provide a clear warning. In agent contexts, implicit filesystem writes can surprise users, overwrite expected workspace organization, or persist sensitive content to disk without informed consent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documented process directs execution of an external conversion script via Bun/NPX without a user-facing warning or consent step. In an agent environment, implicit command execution expands the attack surface significantly by enabling unexpected code execution, dependency resolution, and filesystem/network side effects.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.