ClawHub
Back to skill

Security audit

Ideonomy Engine — Creative Reasoning for AI Agents

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed creative-reasoning helper that installs and uses a global npm CLI, with no evidence of hidden data access or destructive behavior in the artifact.

Before installing, consider whether you trust the npm package publisher because the skill asks for a global CLI install. Use the skill for brainstorming, debugging angles, and structured thinking; avoid sending sensitive problem statements unless you have separately verified how the installed CLI handles data.

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
87% confidence
Finding
The skill description uses broad phrases like 'use when stuck on a problem,' 'need fresh perspectives,' and 'want to think more creatively,' which are generic enough to match a wide range of ordinary user requests. In agent environments, this can cause over-activation or inappropriate routing, leading the skill to intercept queries outside its intended scope and influence behavior unexpectedly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.