ClawHub
Back to skill

Security audit

Anti Centralization Probe

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk instruction-only skill that reviews centralization risks and does not include code execution, credential access, persistence, or hidden data handling.

Reasonable to install if you want proposal or governance reviews for centralization risk. Be aware it may activate when you mention generic dependencies, and treat its output as structural critique rather than financial, legal, or operational advice.

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
This manifest defines generic trigger terms such as "dependency" and "centralization" without narrowing context, scope, or exclusion conditions. In a manifest file, such broad triggers can overlap with ordinary conversation and cause unintended activation because there is no specificity about when the skill should or should not run.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal