ClawHub
Back to skill

Security audit

BrowserAgent

Security checks across malware telemetry and agentic risk

Overview

This is a useful Playwright browser automation guide, but it needs review because it teaches stealthy bot-evasion and persistent logged-in session reuse without enough safeguards.

Install only for authorized browser automation, testing, or accessibility work. Do not use the stealth or anti-detection guidance to bypass third-party site rules. Treat any saved session.json, screenshots, videos, downloads, and extracted data as sensitive; keep them out of version control, restrict access, and delete them when no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly instructs users to persist authenticated browser state to a local session.json file, but it does not warn that this file may contain reusable cookies, tokens, and other session artifacts. In a browser automation skill, that omission is meaningful because copied, reused, or leaked storage state can enable account takeover or unauthorized session reuse.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The screenshot, recording, and download guidance encourages creating local artifacts without warning that they may capture credentials, PII, session details, internal URLs, or other sensitive content. Because this skill is designed for authenticated and dynamic browsing, the risk is elevated: routine use can silently create sensitive files on disk.

Ssd 4

Medium
Confidence
97% confidence
Finding
The skill repeatedly frames bot-evasion as a normal use case and provides concrete anti-detection techniques such as stealth plugins, navigator property spoofing, and human-like interaction simulation. In context, this goes beyond generic browser automation and meaningfully enables circumvention of site defenses, which can facilitate abusive scraping, policy evasion, and unauthorized automation at scale.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal