ClawHub

Visualization Chart Generation

Security checks across malware telemetry and agentic risk

Overview

This skill generates chart files and optional browser-based visualizations, with no evidence of hidden data access, persistence, or exfiltration.

Install only if you want an agent to create visualization files in your workspace. Prefer choosing the output path and filename yourself, and review generated HTML before opening it when it includes JavaScript or external Chart.js/D3.js CDN dependencies.

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
87% confidence
Finding
The trigger list includes broad terms such as '可视化', 'chart', and especially 'meta-skill-system', which can cause the skill to activate in contexts unrelated to explicit chart-generation requests. Over-broad activation increases the chance of unintended file generation or instruction capture, expanding the skill’s effective attack surface.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to save generated output as .svg or .html files and report file locations, but it does not clearly disclose upfront that it may write into the user workspace. In an agent setting, undisclosed filesystem writes can surprise users, overwrite artifacts, or create executable HTML/JS content that users later open in a browser.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal