Back to skill

Security audit

Browser Automation V2 Tool Free

Security checks across malware telemetry and agentic risk

Overview

This is a browser automation skill, but it includes account-login automation and long-running scheduling examples without enough user-control or credential-handling guidance.

Review this before installing if you plan to use it on real accounts. Use dummy or test credentials unless the agent asks for explicit confirmation before login submission, avoid putting passwords in prompts or command arguments, and avoid running the scheduled scraping loop unattended without a clear stop condition.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents automated login form filling and submission without any warning, consent boundary, or credential-handling safeguards. In an agent context, this can normalize collecting, storing, or replaying sensitive credentials and can trigger account actions on external sites without adequate user awareness.

Ssd 3

Medium
Confidence
95% confidence
Finding
The example explicitly handles login credentials in natural-language-driven automation, creating a high-risk pattern for exposing or misusing authentication data. In agent workflows, secrets may be echoed in prompts, command lines, logs, process lists, or tool outputs, increasing the chance of credential leakage or unauthorized account activity.

Unvalidated Output Injection

High
Category
Output Handling
Content
"--timeout", str(timeout),
        "--wait-until", "networkidle"
    ]
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout+10)
    if result.returncode != 0:
        return {"success": False, "error": result.stderr}
    return json.loads(result.stdout)
Confidence
88% confidence
Finding
subprocess.run(cmd, capture_output

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.