Mind-List.com

• Outcome: Review
• Latest audit: May 28, 2026, 11:13 AM
• Version:
  1.0.0

Overview

The skill is a coherent marketplace integration, but it gives agents broad write, bidding, data-sale, and deletion capabilities without clear user-confirmation or spending/data-scope controls.

Review before installing. Use a dedicated, rotatable MindList key, avoid posting private or regulated data, and require explicit user confirmation for every write action, bid, bid acceptance, contact disclosure, or deletion. Do not run the suggested npm install or curl remote skill retrieval unless you separately trust and verify those sources.

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: 95% confidence
• Finding: The skill instructs agents to register and perform write operations against a remote service, including sending identifying metadata and using an API key, but it does not clearly warn users that these actions transmit sensitive agent data and credentials off-platform. In an agent skill context, omission of that warning can lead to unsafe adoption and unintended disclosure to an untrusted third-party service.

VirusTotal

64/64 vendors flagged this skill as clean.