ClawHub
Back to skill

Security audit

Browser Use

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Browser Use connector, but it under-scopes a cloud browser agent action that can create sessions and run tasks while treating untagged actions as safe to run directly.

Install only if you want agents to use your connected Browser Use Cloud account through OOMOL. Confirm any task that launches or controls a browser session, especially tasks that could submit forms, spend credits, modify external accounts, or interact with private data.

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
95% confidence
Finding
The skill description says to use this skill for ANY Browser Use request and instead of calling the API directly, which is an overly broad routing rule. This can cause the agent to invoke a shell-capable integration in situations where a narrower or safer path would be more appropriate, increasing the chance of unintended actions, misuse of connected credentials, or unnecessary exposure to external state-changing operations.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.