ClawHub
Back to skill

Security audit

OpenClaw Browser WSL Attach

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local repair helper for OpenClaw browser automation, with some disruptive setup actions users should approve before running.

Install this only if you want help configuring or repairing OpenClaw browser automation on this machine. Review the scripts before running them, expect ~/.openclaw/openclaw.json to be changed with a backup, and approve any browser restart, process cleanup, or no-sandbox Chromium launch because those actions can interrupt browser work and weaken Chromium isolation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to read and modify user configuration files and execute shell commands, but it does not declare permissions or clearly scope those capabilities. This creates a transparency and control problem: a caller may trigger file writes and command execution without an explicit permission boundary, increasing the chance of unintended system changes.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The activation text is very broad and can match ordinary browser-related requests such as screenshots, page extraction, login flows, clicking, or typing. In context, that broad trigger surface is risky because this skill does more than normal browsing: it changes config, restarts services, and starts or kills browser processes, so it could be invoked when the user only intended a routine browser action.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documented workflow includes modifying ~/.openclaw/openclaw.json and killing stale Chromium processes on port 18800, but it does not require a user warning or confirmation before doing so. Those actions can terminate active browser sessions, disrupt unrelated work, or alter persistent automation settings, which is especially dangerous in shared, root-run, headless, or WSL environments described by the skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.