ClawHub
Back to skill

Security audit

ScrapeGraphAI

Security checks across malware telemetry and agentic risk

Overview

This is a small, disclosed connector skill for using ScrapeGraphAI through OOMOL's oo CLI, with no hidden files or malicious scanner signals.

Install this only if you intend to use ScrapeGraphAI through an OOMOL-connected account and the oo CLI. Searches, scraping targets, prompts, and extraction inputs may be sent to the connector service, so avoid submitting sensitive private pages or data unless that is intended.

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
95% confidence
Finding
The activation text is extremely broad: it instructs the agent to use this skill for ANY ScrapeGraphAI request and whenever a task involves ScrapeGraphAI. That can cause unintended invocation based on loose keyword matching or indirect mentions, increasing the chance the agent performs external searches/scrapes when the user did not explicitly ask for that tool or when a safer/native path exists.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.