ClawHub
Back to skill

Security audit

Edge Browser

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward browser-fetch helper with disclosed network access and optional file output, with no evidence of hidden or malicious behavior.

Install only if you are comfortable adding Playwright/Chromium and letting the agent fetch specific URLs. Avoid using it on sensitive internal or authenticated pages unless intended, quote URLs safely when invoking from a shell, and choose --output paths carefully because existing writable files can be overwritten.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The script accepts an arbitrary --output path and writes fetched page content there, while the skill is described only as browser fetch/extraction. In an agent setting, this creates an undeclared file-write capability that can overwrite user files, place sensitive fetched data in unexpected locations, or be abused as part of a larger chain if an attacker can influence the output path.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.