Browser Auto Plus

• Outcome: Review
• Latest audit: Jun 5, 2026 at 5:25 AM UTC
• Version:
  2.0.0

Overview

The skill is a non-executable browser automation guide, but it includes instructions for CAPTCHA avoidance, stealth behavior, proxy anonymity, and anti-detection scraping that need review before installation.

Review this skill carefully before installing. It does not appear to contain a malicious payload, but its documentation encourages stealthy scraping and anti-bot evasion. Use it only for sites and accounts where you have explicit authorization, and avoid the CAPTCHA bypass, proxy-rotation, and stealth-plugin guidance.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The skill is presented as general browser automation and scraping, but its documented features explicitly include proxy anonymity, CAPTCHA solving, stealth plugins, and anti-detection techniques. That mismatch increases misuse risk because it packages evasion capabilities as ordinary automation, making abusive scraping, access-control circumvention, and harder-to-detect automation easier.

Context-Inappropriate Capability

High

• Confidence: 97% confidence
• Finding: This section gives concrete anti-detection guidance including randomized delays, user-agent rotation, viewport randomization, proxy rotation, and human-like behavior. In the context of a browser automation skill, those instructions materially increase the capability to evade bot detection and platform defenses, which goes beyond normal testing or accessibility automation.

Context-Inappropriate Capability

High

• Confidence: 98% confidence
• Finding: The CAPTCHA section documents detection plus manual or automatic solving, proxy rotation, and stealth plugins as workflow steps. CAPTCHA mechanisms are commonly used as abuse-prevention controls, so guidance on solving or bypassing them facilitates circumvention of security and anti-bot protections.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill promotes proxy support for anonymity together with web scraping, but does not include warnings about privacy, consent, terms-of-service, or legal constraints. That omission makes risky collection and anonymized scraping appear routine, increasing the chance of misuse against sites or data subjects.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The anti-detection and CAPTCHA-evasion guidance is provided without any warning that these techniques may violate site policies or be used to bypass abuse protections. In context, the lack of disclosure increases danger because the skill normalizes evasion as a standard operational practice.

VirusTotal

64/64 vendors flagged this skill as clean.