ClawHub
Back to skill

Security audit

Webpage Export

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it fetches user-provided webpages and saves local TXT, DOCX, PDF, and metadata outputs, with browser rendering disclosed as an optional fallback risk.

Install only if you are comfortable with the agent fetching URLs and writing local exports. Prefer explicit output folders, use trusted local Chrome/Node/Playwright installations, and avoid giving it localhost, private-network, file, cloud-metadata, or sensitive logged-in pages unless you intend the local browser/fetch tools to access them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
'HOME': os.environ.get('HOME', ''),
        'CHROME_BIN': chrome,
    }
    subprocess.run([
        'node',
        '-e',
        script,
Confidence
92% confidence
Finding
subprocess.run([ 'node', '-e', script, url, str(out_path), ], check=True, env=child_env)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
chrome = chrome_path()
    if not chrome:
        raise RuntimeError('未找到 Chrome/Chromium，无法生成 PDF')
    subprocess.run([
        chrome,
        '--headless=new',
        '--disable-gpu',
Confidence
90% confidence
Finding
subprocess.run([ chrome, '--headless=new', '--disable-gpu', '--no-first-run', f'--virtual-time-budget={virtual_time_budget}', f'--print-to-pdf={pdf_

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill clearly instructs the agent to invoke local scripts and system tools (`python3`, `curl`, Chrome/Chromium, Node/Playwright, `textutil`) and to read/write files, but it declares no corresponding permissions. That mismatch is a real security issue because it hides the skill's operational capabilities from any permission or policy layer, increasing the chance that an agent executes network, shell, and filesystem actions without explicit review.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.