ClawHub
Back to skill

Security audit

RedFoxHub

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed RedFoxHub read/search connector that uses the OOMOL CLI and does not show hidden, destructive, or exfiltrating behavior.

Install this only if you intend to let Codex query RedFoxHub through your OOMOL-connected account. Be cautious with the one-time CLI install/login steps, verify the OOMOL and RedFoxHub connection pages, and require explicit approval before any future action that is marked write or destructive.

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
91% confidence
Finding
The skill directive says to use this skill for ANY RedFoxHub request, which creates an overly broad trigger scope and can cause the agent to route unrelated or higher-risk RedFoxHub tasks through this skill automatically. In context, the skill exposes a shell-capable tool path and includes operational setup steps, so broad mandatory routing increases the chance of unsafe invocation, overreach, or bypass of narrower task-specific safeguards.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal