ClawHub
Back to skill

Security audit

Ui Component Tool Free

Security checks across malware telemetry and agentic risk

Overview

The skill is a local HTML/CSS component generator, but it asks for broad write and command execution access with loose routing beyond its narrow purpose.

Install only if you are comfortable granting command execution to a UI component helper. Prefer using it for explicit HTML/CSS component generation, review any proposed shell command before it runs, and avoid letting it handle unrelated debugging, deployment, or system/network troubleshooting tasks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The skill is presented as a local HTML/CSS component generator, yet it requests `exec` capability, which is far broader than needed for simple code generation. This creates unnecessary command-execution exposure and increases the chance that an agent may run shell commands based on user or skill instructions, violating least privilege.

Intent-Code Divergence

Medium
Confidence
89% confidence
Finding
The documentation says no extra scripts or dependencies are required, but elsewhere the skill is classified as MD+EXEC and states some functions need command execution. This inconsistency can mislead users and agents about the privilege level required, causing execution capabilities to be granted under false assumptions.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger conditions are broad enough to activate on generic developer tasks such as coding assistance, debugging, testing, and deployment. Over-broad routing can cause this skill to be invoked outside its narrow UI-generation purpose, increasing the chance that its unnecessary `exec` capability is exposed in unrelated contexts.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.