ClawHub
Back to skill

Security audit

Nova Perspective Router

Security checks across malware telemetry and agentic risk

Overview

This is a local keyword-based router for choosing expert-style perspectives, with broad activation wording but no evidence of hidden access, persistence, credential use, or destructive behavior.

Install this if you want Nova to automatically suggest expert-style perspectives for complex analysis. Review or narrow the trigger phrases if you prefer explicit opt-in routing, because the skill may influence the style and framing of ordinary analysis responses.

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

Medium
Confidence
91% confidence
Finding
The skill says it should run whenever tasks involve professional analysis, multiple perspectives, or when Nova is unsure which expert to call. That trigger scope is broad and subjective, making accidental invocation likely across many normal conversations and increasing the chance that persona-routing alters responses unexpectedly or causes unnecessary downstream skill loading.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The listed trigger phrases include very common language such as asking for business analysis or whether a strategy is good. Because these phrases overlap with ordinary requests, the router may activate in benign contexts and steer the agent into expert-persona workflows the user did not clearly request.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal