Browser Read

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

Overview

This skill is a straightforward browser page text extractor, with the main caution that it can read visible content from logged-in pages you choose to process.

Install only if you want an agent to extract text from browser pages you open for it. Avoid using it on private messages, account settings, dashboards, or other sensitive logged-in pages unless you are comfortable with the visible page text and URL being returned to the agent.

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: The skill explicitly targets pages that may be authenticated or otherwise inaccessible to normal fetching, but it does not warn that extraction will read whatever content is visible in the current browser session, including private or account-scoped data. This creates a realistic risk of over-collection and unintended disclosure because a user or downstream agent may invoke it without realizing it can capture sensitive session-bound content from Twitter/X, LinkedIn, or other logged-in sites.

VirusTotal

66/66 vendors flagged this skill as clean.