Browser Agent Trust Hub

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:44 PM UTC
• Version:
  1.0.0

Overview

This skill is a local browser-agent policy checker that reads scoped JSON inputs and produces a trust report without browsing, credentials, or hidden background behavior.

Install this if you want a local pre-flight checker for browser-agent workflows. Keep policy and action JSON files inside the skill directory, avoid placing real secrets in those files, and review generated REVIEW or BLOCK results before allowing a browser agent to take live actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

65/65 vendors flagged this skill as clean.