ClawHub
Back to skill

Security audit

Decision Trees

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward decision-tree helper with an optional local calculator and no evidence of hidden access or unsafe automatic behavior.

Reasonable to install for structured decision analysis. Use it as a thinking aid, avoid treating its expected-value output as financial, legal, medical, or business advice, and only run the calculator on files and save paths you intentionally choose.

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
86% confidence
Finding
The trigger list includes very broad phrases such as 'should I', 'what if', 'evaluate options', and 'compare alternatives', which can match a large fraction of ordinary user conversations. This can cause the skill to activate in contexts where structured decision-tree reasoning is unnecessary or inappropriate, potentially crowding out safer or more domain-specific handling, especially for sensitive areas like finance, health, or legal decisions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.