mcp-server-discovery-p

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:42 PM UTC
• Version:
  1.0.0

Overview

This is a coherent MCP server lookup and config helper, but users should review generated configs before enabling powerful downstream MCP servers.

Before installing or using generated MCP configs, review each selected server, prefer trusted and pinned packages where possible, and grant filesystem paths, database access, memory, and API tokens only where needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (2)

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The description is broad enough to match generic MCP, server discovery, configuration, and integration requests, which can cause the skill to activate outside a narrowly intended scope. Overbroad triggering increases the chance that users are steered into running discovery/configuration workflows unnecessarily, including network-backed operations or generation of sensitive client configs in contexts where they did not expect it.

Missing User Warnings

Low

• Confidence: 72% confidence
• Finding: The workflow instructs users to generate configuration and save it to an MCP client's config file without warning about overwrite risk, environment-specific paths, or the need to review generated content before applying it. This can lead to accidental configuration corruption, replacement of existing trusted settings, or adoption of unsafe endpoints if the generated config is used blindly.

VirusTotal

66/66 vendors flagged this skill as clean.