ClawHub
Back to skill

Security audit

Web Scraper Seller

Security checks for vulnerabilities and agentic risk

Overview

The skill is a web-scraping service listing with no executable payload, but it advertises broad scraping and monitoring without clear authorization, privacy, or terms-of-service boundaries.

Review this carefully before installing or using it. Only use scraping for sites and data you are authorized to collect, avoid personal or credentialed data, respect site terms and rate limits, and require clearer safeguards from the publisher before using scheduled, unlimited, or full-site scraping.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill advertises it can build custom web scrapers for any website, which is an overly broad capability statement that could be triggered for sensitive, policy-violating, or unauthorized scraping tasks without guardrails. In the context of an agent skill marketplace, this ambiguity increases the chance the skill will be used for data harvesting, bypassing site restrictions, or other integrity-affecting automation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description contains no warnings or restrictions around sensitive data collection, consent, robots.txt/terms compliance, rate limiting, or anti-abuse boundaries. Because the service offers multi-page, unlimited, scheduled, and real-time scraping, the lack of safety language makes misuse materially easier and increases the risk of privacy, legal, and operational harm.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.