browser-read-x

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:23 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed browser-page text extractor for X/Twitter, with privacy risk if the user runs it on a sensitive page but no evidence of hidden exfiltration or persistence.

Install only if you are comfortable with a tool that can read and return text from the currently open browser page. Use it on the X/Twitter post or article you intend to extract, and avoid running it on private messages, email, account settings, internal tools, or other sensitive pages.

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 (1)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: This script extracts the full visible page text, metadata, and current URL from whatever page is open and returns it to the caller with no in-skill consent check, origin restriction, or data minimization. In an agent setting, that can expose sensitive information from authenticated pages, private posts, DMs, account data, or other browser-visible content beyond the user's likely expectation for a 'read X post/article' helper.

VirusTotal

66/66 vendors flagged this skill as clean.