ClawHub
Back to skill

Security audit

Label Studio

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Label Studio connector guide with disclosed read and write actions and no evidence of hidden or destructive behavior.

Install this only if you want agents to use OOMOL's oo CLI for Label Studio work. Be aware it can read Label Studio data visible to your connected API key, and creating projects or tasks should only happen after you review the exact payload and approve the change.

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
89% confidence
Finding
The trigger phrase is explicitly broad: 'Use this skill for ANY Label Studio request' and 'Whenever a task involves Label Studio, use this skill instead of calling the API directly.' This can cause the agent to route any mention of Label Studio through this skill, even when the user only wants discussion, analysis, or a different integration path, increasing the chance of unintended tool invocation and unnecessary access to connected data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.