ClawHub
Back to skill

Security audit

Code Flow Visualizer

Security checks across malware telemetry and agentic risk

Overview

This is a simple code-to-flowchart helper with no evidence of hidden access, persistence, or unsafe execution.

Install if you want an agent to turn code snippets into Mermaid flowcharts. Be aware that generic flowchart requests may activate this skill, so use explicit prompts when you want a different diagramming tool, and review generated Mermaid before rendering sensitive code in external viewers.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger patterns are generic terms such as 'flowchart' and '代码流程图' without constraints on code size, language, repository scope, or explicit user intent. This can cause the skill to activate unexpectedly in unrelated contexts, potentially exposing user-supplied code to unintended processing and increasing the attack surface for prompt/skill routing abuse.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.