ClawHub

Advanced Dispatcher

Security checks across malware telemetry and agentic risk

Overview

This skill transparently routes tasks to selected AI models and does not show hidden installation, credential access, persistence, or destructive behavior.

Before installing, understand that the skill is meant to route your task content to different spawned model providers and some OpenAI routes use long cache retention. Use explicit prompts for build or tradeoff workflows, avoid sending secrets unless the provider and retention behavior are acceptable, and review any code changes produced by build pipelines before merging.

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 description is extremely broad and advertises activation for many common task types, which increases the chance it will be invoked when a narrower, more appropriate skill should handle the request. In an agent system, over-broad activation can cause unintended routing behavior, unexpected spawned-model use, and policy bypass-by-misclassification even without malicious intent.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The tradeoff trigger of phrases like asking 'which is better' is ambiguous because it overlaps with ordinary conversation and can activate multi-model comparison logic unexpectedly. In this skill, that matters because tradeoff mode changes routing behavior and can enable Claude proposals when `--force-claude` is present, so accidental entry into this path expands model-selection surface.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal