ClawHub
Back to skill

Security audit

Browser Automation

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Puppeteer browser automation skill whose web access and screenshot/scraping behavior are disclosed and aligned with its purpose.

Install this only when you want an agent to run a real headless browser against sites you choose. Review site terms, robots.txt, and rate limits, and avoid using it on logged-in, payment, or sensitive account pages unless you explicitly intend that automation.

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 manifest description includes broad trigger phrases such as "extract data from," "take screenshot of," and "any request involving Puppeteer or headless browser automation," which can cause the skill to be selected for a wide range of generic requests. Because this skill performs active browser automation and network access, overbroad routing increases the chance it is invoked in contexts where a safer, narrower tool should be used, potentially expanding exposure to scraping, navigation, and local file output behaviors.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill introduces Puppeteer-based scraping and automation without an upfront warning that the examples initiate outbound network requests and may write artifacts such as screenshots to local disk. In an agent setting, missing this disclosure can mislead operators or downstream systems about side effects, making unintended browsing, scraping, or filesystem writes more likely.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.