ClawHub
Back to skill

Security audit

OpenClaw Memory Kit

Security checks across malware telemetry and agentic risk

Overview

This is a transparent setup guide for an OpenClaw memory workspace, with privacy safeguards and no hidden executable code in the reviewed files.

Install only if you want a persistent OpenClaw memory workspace. Use an isolated target directory, keep real tokens and .env files out of shared kits, review any bootstrap script before running it, and periodically inspect or delete generated memory and task files if they may contain sensitive information.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill enables implicit invocation without defining narrow trigger constraints, so an agent may activate this capability in broader contexts than intended. Because this skill scaffolds, sanitizes, and shares memory-system workspaces and configuration, unintended activation could cause accidental handling, transformation, or exposure of sensitive project memory assets or configs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal