ClawHub
Back to skill

Security audit

ScrapingAnt

Security checks across malware telemetry and agentic risk

Overview

This is a coherent ScrapingAnt connector skill, with disclosed OOMOL account use and optional CLI setup that users should review before running.

Install this only if you want your agent to use your OOMOL-connected ScrapingAnt account for scraping and extraction. Verify the `oo` CLI installation path before running remote installer commands, and remember that scraping actions may return page HTML, text, headers, cookies, XHRs, and iframe data from URLs you provide.

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 description says to use this skill for ANY ScrapingAnt request and whenever a task involves ScrapingAnt, which is an overly broad trigger. That can cause the agent to invoke this skill even for incidental mentions, increasing the chance of unintended external actions, credentialed connector use, or bypassing safer/more specific handling paths.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.