Back to skill

Security audit

MCP Precheck

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed MCP-server precheck helper that runs PolicyLayer lookups before connecting to MCP servers and asks for approval before making persistent changes.

Before installing, understand that this skill relies on the external PolicyLayer CLI and registry, and MCP server names or package identifiers may be looked up remotely. The optional hook changes Claude settings and should only be installed if you want automatic prechecks on future MCP additions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.