ClawHub
Back to skill

Security audit

dashboard-builder-free

Security checks across malware telemetry and agentic risk

Overview

This is a local dashboard-building skill whose file, command, API-key, and cron guidance is mostly disclosed and aligned with its purpose, but users should review generated scripts and keep dashboards local.

Install only if you want an agent to create local dashboard files and fetch scripts. Review any generated `fetch.sh`, use least-privilege API keys from environment variables, avoid hardcoding secrets, and bind previews to `127.0.0.1`; do not publish the dashboard without adding authentication and access controls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The documentation states the dashboard should be localhost-only, but the example URL tells users to access `https://example.com/8080`, which contradicts the local-only safety model and can normalize public exposure. In a skill that generates dashboards and local servers, misleading network-access guidance can cause users to bind or publish services insecurely.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger condition is overly broad (`需要数据分析、报表生成、统计洞察、数据可视化时使用`), which increases the chance this skill activates for generic requests and then uses `exec`, `write`, and credential-handling flows unnecessarily. In a high-privilege skill that can generate scripts and run commands, over-triggering materially raises the risk of unsafe or unintended actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill combines script generation, file writes, command execution, scheduled jobs, and use of sensitive API credentials, but lacks a centralized and explicit risk notice describing these actions and their consequences. In this context, users may unknowingly authorize creation of executable fetch scripts or credential-dependent automation, increasing the likelihood of unsafe execution, data leakage, or persistent risky configuration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.