ClawHub
Back to skill

Security audit

generate-mindmap

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed mind-map generation guide, with some overly broad trigger wording and optional dependency installation that users should control.

Install this only if you want an agent to help generate mind maps and export files. Use it for explicit mind-map requests, review output paths before running commands, and use --no-auto-install in shared or locked-down environments if you do not want the agent attempting to install Pillow.

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

High
Confidence
89% confidence
Finding
The trigger keywords are overly broad and generic, including terms like 'generate', 'html', and '支持', which can cause the skill to activate for unrelated user requests. In an agent environment that can execute commands, unintended invocation increases the chance of unnecessary file creation, local command execution, or dependency installation without clear user intent.

Vague Triggers

High
Confidence
88% confidence
Finding
The repeated broad trigger list in the core capabilities section reinforces ambiguous activation conditions and increases the likelihood of accidental skill routing. Because this skill's workflow includes command-line execution and optional package installation, false activation is more dangerous than a purely informational skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.