ClawHub
Back to skill

Security audit

Shadows MCP Forge

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward MCP server scaffolding guide with its file-writing and dependency suggestions disclosed and aligned with its purpose.

Install this if you intend to build new MCP servers. Review any generated code and package names before running installs, keep secrets in environment variables as instructed, and avoid invoking it for ordinary REST API projects or existing MCP server configuration tasks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger conditions are broad enough that the skill may activate on generic phrases like 'create a tool server' or 'MCP server' without strong context checks. In an agent environment, over-broad activation can cause the wrong skill to scaffold code, suggest package installs, or steer the conversation toward code generation when the user intended something else.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.