ClawHub
Back to skill

Security audit

Web Scraper

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed web-scraping helper, but users should use it only on sites and data they are allowed to collect.

Install only if you need browser-based scraping. Confirm the target site permits scraping, avoid collecting personal or sensitive data without a lawful basis, do not use proxy or CAPTCHA-bypass tactics unless clearly authorized, and review the output path before running.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The anti-scraping section includes operational guidance for bypassing protections such as IP blocking, CAPTCHA, rate limiting, and JavaScript challenges. This goes beyond neutral scraping documentation and materially enables evasion of access controls and website defenses, which raises abuse risk and legal/compliance exposure.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly mentions scraping contact information and exporting results to CSV/JSON/Excel, but it does not present a clear warning about collecting, storing, and sharing personal data. In context, this omission makes the skill more dangerous because it normalizes bulk extraction of potentially regulated personal information without adequate privacy safeguards.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The script accepts an arbitrary URL and instructs an external browser agent to open it and extract content, with no restriction on schemes, hosts, or destination trust level. In an agent skill context, this can be abused for unintended access to internal resources, sensitive local services, or privacy-impacting scraping if the surrounding environment grants the browser broader network or credential access.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.