ClawHub
Back to skill

Security audit

nse-orchestrator

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed orchestration skill for identity, memory, wallet, calendar, social, and alignment checks, with sensitive-use caveats but no evidence of hidden or malicious behavior.

Install only if you trust the external Python package and any optional pillar packages. Use a test identity and limited wallet first, never paste nsec values or seed phrases into chat, and require explicit confirmation before payments, public profile updates, calendar changes, or persistent memory writes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation guidance uses very broad phrases such as 'set up NSE' or 'become a sovereign entity,' and later encourages use in many 'important' or 'significant' situations without defining hard boundaries. In an agent-skill context, vague triggers can cause over-invocation in sensitive workflows involving identity, payments, memory, and alignment, increasing the chance the skill is activated when it should not be.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill instructs the user to generate a cryptographic identity and references an nsec keypair and 12-word seed phrase backup, but it does not prominently warn that these secrets must never be pasted into chat, logged, routed through the orchestrator, or exposed to third parties. In this context, the skill centers on sovereign identity and persistent memory, so under-warning users about irreversible key/seed compromise materially increases the risk of account takeover and permanent loss of control.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal