Handy01 Agent Browser

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  0.1.2

Overview

This is a disclosed Playwright browser-automation skill, but users should treat saved browser state and cookies as sensitive.

Install only if you need browser automation. Do not use it on personal or production accounts unless necessary, and treat saved state files, cookies, localStorage, sessionStorage, persistent profiles, screenshots, traces, and videos as sensitive secrets. Prefer isolated test accounts and delete saved auth state after the task.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill explicitly documents saving and loading browser auth state, which commonly includes session cookies and local storage tokens, but provides no warning about their sensitivity or safe handling. In an agent context, this increases the chance that credentials are written to disk, reused across tasks, or exposed to other users/processes, enabling account takeover if the saved state is leaked.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation exposes commands to read and modify cookies and browser storage without any caution that these values may contain session identifiers, CSRF tokens, or other secrets. In a skill designed for AI agents, that omission is risky because agents may inspect, persist, or alter sensitive browser state in ways that leak credentials or corrupt authenticated sessions.

VirusTotal

64/64 vendors flagged this skill as clean.