ClawHub
Back to skill

Security audit

Refiner

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Refiner connector helper with clear read, write, and destructive-action warnings, and no hidden code or malware signals were found.

Install only if you intend to let your agent operate your Refiner workspace through OOMOL. Review payloads carefully before approving write or destructive actions, and only use the remote oo CLI installer and OOMOL connection flow if you trust that provider.

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
84% confidence
Finding
The skill description says to use this skill for ANY Refiner request and instead of calling the API directly, which creates an overly broad routing trigger. That can cause the agent to invoke this skill for unrelated or higher-risk Refiner tasks without sufficient narrowing, increasing the chance of unintended reads, writes, or destructive operations being attempted under vague user requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.