URL to Markdown

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:45 PM UTC
• Version:
  2.1.2

Overview

The skill’s remote fetching behavior appears aligned with its purpose, but users should be careful with authenticated or sensitive URLs.

Install if you want the agent to fetch web content, but only provide URLs and authentication tokens for destinations you trust. Avoid embedding secrets in URLs, prefer short-lived or least-privilege tokens, and do not fetch private internal endpoints unless you understand what will be sent to the remote server.

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: 90% confidence
• Finding: This skill instructs users to fetch arbitrary remote URLs and explicitly notes that login-required content may need authentication tokens, but it does not warn that supplying such tokens or fetching external URLs can disclose sensitive credentials, IP/user-agent information, or contextual data to third-party servers. In an agent setting, this omission is security-relevant because users may assume the operation is low risk and provide secrets or internal URLs without understanding the exposure.

VirusTotal

65/65 vendors flagged this skill as clean.