ClawHub
Back to skill

Security audit

Browser Config

Security checks across malware telemetry and agentic risk

Overview

This is a small OpenClaw-CN browser configuration guide with disclosed local config and browser-session effects, not an executable or hidden-behavior package.

Install this if you want help configuring OpenClaw-CN browser mode. Before applying its examples, confirm you mean to change OpenClaw-CN settings, back up openclaw.json if needed, and be careful with Chrome mode because it can use existing browser login sessions.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are generic operational requests such as configuring or fixing a browser, which can overlap with many ordinary user intents and cause the skill to be invoked unexpectedly. In an agent setting, ambiguous invocation increases the chance that configuration-changing instructions or browser-management actions are applied in the wrong context, especially because this skill edits persistent settings and influences browser/session behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.