Back to plugin

Security audit

Nowledge Mem

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed memory plugin that persistently captures and searches OpenClaw conversation history, so it is privacy-sensitive but coherent with its stated purpose.

Install only if you want OpenClaw conversations and selected memories to become part of a persistent Nowledge Mem knowledge graph. Review whether you want local-only or remote mode, keep API keys scoped, and disable sessionDigest or use captureExclude/#nmem-skip for conversations you do not want captured.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation guidance is broad enough to match very common phrases like 'remind me' or references to prior work, which can cause the memory skill to be invoked in many ordinary conversations. Because the skill can search and proactively save cross-source personal knowledge, over-triggering increases the chance of unnecessary retrieval or persistence of sensitive user content without an explicit, contextual consent step.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill explicitly instructs proactive saving of conversation content and states that memories span multiple sources, but it provides no upfront warning or consent mechanism to the user. In a memory tool handling cross-AI history, decisions, preferences, and thread data, this omission creates a significant privacy risk because users may not realize their content is being persisted and correlated across systems.

VirusTotal

61/61 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.