ClawHub

Universal Extractor

Security checks across malware telemetry and agentic risk

Overview

This is a coherent paid text-extraction skill, but users should treat submitted URLs and files as shared with an external service.

Install only if you are comfortable sending selected URLs, filenames, and file contents to this third-party extraction service. Avoid confidential, regulated, personal, or credential-containing documents unless you have approval, and use wallet or platform controls for the disclosed USDC per-request charges.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The skill description is overly broad and can cause the agent to invoke this skill for many loosely related requests involving reading, summarizing, or extracting content. That increases the chance of unnecessary data exfiltration to an external service, especially when users did not explicitly ask to send URLs or files off-platform. In this context, the skill handles arbitrary URLs and uploaded documents, so overbroad routing is more dangerous than for a narrowly scoped local-only utility.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents sending URLs and base64-encoded document contents to external micro-services but does not warn that page contents, files, and potentially sensitive documents are transmitted off-platform. Users and orchestrators may therefore route confidential material to third-party services without informed consent. Because this skill explicitly supports arbitrary documents and files, the risk includes leakage of proprietary, personal, legal, or regulated data.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal