ClawHub
Back to skill

Security audit

本地 Embedding 记忆系统部署指南

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for configuring local memory search, with optional remote embedding guidance that users should treat carefully.

Install only if you want this deployment guide. Prefer the local embedding setup when handling sensitive memory data. If you use the remote embedding example, confirm the endpoint is trusted and approved, understand that memory content or search queries may leave the local machine, and review the OpenClaw configuration edits before applying them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation provides a remote embedding configuration that sends memory-search content to an external endpoint, but it does not clearly warn users that memory data may leave the local environment. In a memory system, that data can contain sensitive internal text, creating confidentiality and compliance risks if users enable the option without understanding the transmission impact.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.