ClawHub
Back to skill

Security audit

omni-scraper

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed external web-scraping integration, but users should avoid sending sensitive URLs or page data through it.

Install only if you are comfortable routing requested URLs and returned page content through Claw School's service. Do not use it for internal systems, localhost/private-network URLs, authenticated pages, signed links, or sensitive query parameters unless that data sharing has been approved. Store the CLAW_KEY as a secret.

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
93% confidence
Finding
The trigger phrases are very broad (e.g. scrape, crawl, fetch page, get product data), which increases the chance the skill is invoked for requests the user did not specifically intend to send to this external service. Because the skill transmits arbitrary URLs and potentially page contents to a third-party scraper, accidental invocation can cause unintended data disclosure and unreviewed outbound requests.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs the agent to send user-supplied URLs and receive page data through an external scraping provider, but it does not clearly warn users that both the requested target and returned content may be processed by a third party. This omission can lead to privacy, confidentiality, and compliance issues if users provide internal, authenticated, or otherwise sensitive URLs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.