ClawHub
Back to skill

Security audit

neural-memory

Security checks across malware telemetry and agentic risk

Overview

This is a real persistent memory skill, but it enables broad automatic capture and recall of conversation context by default and exposes additional indexing, sync, and backup tools that need careful review.

Install only if you want an agent-wide persistent memory layer. Review the OpenClaw config before enabling it, consider setting autoCapture, autoContext, autoFlush, and autoConsolidate to false until you opt in, and avoid storing secrets, credentials, regulated data, or private conversations unless you have a retention and deletion plan.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill instructs proactive use in very broad situations like starting any new task, remembering context across sessions, and after decisions or errors. In combination with a memory tool that persists data and can auto-inject context, this can cause over-invocation, unnecessary retention of user data, and retrieval of irrelevant or sensitive prior context without a clear user-triggered need.

Missing User Warnings

High
Confidence
98% confidence
Finding
The plugin description advertises automatic context injection and auto-capture after agent runs, but does not present a prominent warning that conversation content may be persistently stored locally. Users may unknowingly disclose sensitive data that is then retained across sessions, increasing privacy, compliance, and accidental data exposure risks.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

View on VirusTotal

Static analysis

No suspicious patterns detected.