ClawHub

Smart Router Omni

Security checks across malware telemetry and agentic risk

Overview

This is a routing-only skill that inspects visible skill metadata to recommend a skill or chain, with no executable code, credential access, network calls, or persistence.

Install this if you want automatic help choosing skills. Consider disabling implicit invocation or invoking it explicitly in workspaces where installed skill metadata and OpenClaw markers are sensitive. Review any recommended skill chain before letting downstream skills perform browser, publishing, memory, or account-bound actions.

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
94% confidence
Finding
The skill description is extremely broad and can activate on many ordinary requests, effectively positioning this router as a catch-all dispatcher. In a skill ecosystem, overbroad activation increases the chance that this skill intercepts tasks unnecessarily, inspects local metadata and environment signals, and influences downstream routing in ways the user did not explicitly request.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The default prompt is broadly phrased to invoke this router whenever a user asks to inspect the environment and choose the best skill or skill chain, which can cause the router to activate in situations beyond explicit user intent. Because this skill is designed to inspect local environment signals and installed skills, unintended activation increases the chance of unnecessary metadata exposure, over-broad routing, or chaining into higher-risk skills without clear authorization.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal