ClawHub
Back to skill

Security audit

ScraperAPI MCP

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed ScraperAPI reference skill for web scraping and structured data tools, with expected API-key and external-service use but no evidence of hidden or malicious behavior.

Install only if you are comfortable sending target URLs, searches, and scraped content through ScraperAPI and storing a ScraperAPI API key for MCP use. Use it only for authorized scraping, keep crawl patterns and budgets narrow, avoid collecting sensitive personal data unless permitted, and approve callback URLs or recurring schedules only after confirming where results will go.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list contains broad, everyday phrases such as 'finding information online' and 'when unsure which ScraperAPI tool to use,' which can cause the skill to activate for many generic web tasks. In context, this is risky because the skill strongly steers the agent toward ScraperAPI tools over built-in web tools, potentially causing unnecessary external requests, broader data exposure, and tool misuse outside the intended scraping-specific scenarios.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The guide explicitly promotes proxy rotation, CAPTCHA handling, and anti-bot bypass techniques without any accompanying boundaries around authorization, terms-of-service, privacy, or lawful use. In a skill intended to help users choose and optimize scraping tools, this omission can normalize or facilitate collection of protected content and transmission of sensitive target URLs to a third-party scraping service.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.