ClawHub
Back to skill

Security audit

Agent Browser Cn

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate browser automation skill, but it gives an agent broad control over logged-in browser sessions without enough privacy and approval guardrails.

Install only if you trust the external agent-browser CLI and need agent-driven browser automation. Use a separate browser profile or test account, avoid sensitive logged-in sites where possible, and require explicit approval before the agent reads cookies/storage, enters credentials, uploads files, submits forms, saves auth state, records sessions, or changes account data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly documents setting HTTP basic-auth credentials and saving/loading browser session state, but does not warn that these values may contain secrets such as passwords, cookies, bearer tokens, or authenticated browsing context. In an agent setting, this can lead to accidental credential disclosure to logs, files, screenshots, traces, or later tasks that reuse persisted state.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The recording/tracing features capture page activity and explicitly preserve cookies/storage from the current session, but the documentation lacks a privacy and secret-handling warning. This is risky because recordings, traces, and derived artifacts may expose authenticated content, personal data, tokens, and account activity to anyone with access to the saved files.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.