ClawHub
Back to skill

Security audit

Winston AI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Winston AI connector wrapper that sends user-provided text or URLs to Winston AI through OOMOL, with no hidden scripts or destructive behavior found.

Install this only if you are comfortable routing Winston AI-related analysis through OOMOL and sending the selected text or public URLs to Winston AI. Avoid submitting confidential or regulated content unless your Winston AI and OOMOL account policies allow it.

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
90% confidence
Finding
The trigger text is unusually broad: it directs the agent to use this skill for ANY Winston AI request and whenever a task involves Winston AI, rather than narrowing invocation to specific user intents or safe operation classes. That can cause unintended routing of loosely related requests into this skill, increasing the chance of over-collection, unnecessary third-party disclosure of user content, or execution without sufficient user confirmation for sensitive analysis requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.