ClawHub
Back to skill

Security audit

browser-cli-tool-free

Security checks across malware telemetry and agentic risk

Overview

This browser automation skill is mostly coherent, but it needs review because its trigger is mismatched and it encourages automated form submission, scheduled actions, and screenshots without enough safety boundaries.

Install only if you explicitly want an agent to control a browser through a CLI. Review any generated scripts or cron entries before enabling them, avoid hardcoding passwords or private data, and keep screenshots and extracted page content out of shared or public paths.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

High
Confidence
77% confidence
Finding
The trigger condition is overly broad and mismatched to the skill's stated browser-automation purpose, which can cause an agent to invoke this skill for unrelated analysis tasks. In an agentic environment with exec capability, misrouting tasks into a browser automation skill increases the chance of unintended navigation, interaction with external sites, or unnecessary command execution beyond the user's actual intent.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The skill promotes form submission, scheduled automation, and screenshot capture without warning about credential handling, personal-data capture, sensitive page content, or the operational impact of unattended automation. In context, this is more dangerous because the skill explicitly supports browser control plus exec-based scripting, so users may automate logins, submissions, and captures that expose secrets or collect sensitive data without safeguards.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.