ClawHub
Back to skill

Security audit

浏览器智能代理工具-免费版

Security checks for vulnerabilities and agentic risk

Overview

This browser-automation skill is mostly coherent, but its activation scope is too broad and it under-warns about saved browser login state.

Review before installing. Use this skill only for explicit browser automation tasks, avoid invoking it for general coding or deployment help, and treat any state files such as auth.json, admin-auth.json, or user-auth.json as secrets that should not be committed, shared, or reused across accounts. Install the npm CLI only if you trust the package and are comfortable with global native-browser tooling.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger condition is extremely broad, effectively matching generic AI, coding, and orchestration requests rather than narrowly scoped browser-automation tasks. Over-broad activation increases the chance that the skill is invoked in unrelated contexts, where its exec/browser/write capabilities could be unnecessarily exposed and cause unintended command execution, network access, or data handling.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The manifest description includes broad development-assistance and deployment-oriented usage language that extends far beyond a narrowly defined browser automation skill. In agent ecosystems, vague activation scope can cause unsafe tool routing, leading the model to select a skill with exec/browser/write access for tasks that do not require it.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill supports saving and loading browser state, including cookies and storage, but does not provide a strong warning that these files may contain active session tokens, authentication artifacts, or other sensitive data. In a browser automation context this is especially dangerous because reused state files can enable account takeover, cross-session leakage, or accidental persistence of privileged sessions.

Static analysis

No suspicious patterns detected.