Back to skill

Security audit

Shadow Memory - 项目状态持久化 MCP Server

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local project-memory MCP workflow with persistence that matches its stated purpose.

Before installing, use a trusted source for the referenced protocol repository, inspect the MCP server code you clone, and store the .origin package somewhere project-specific. Treat committed facts, decisions, and task history as persistent project data, and avoid placing secrets or private material in memory unless that is intentional.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.