ClawHub
Back to skill

Security audit

Atomic Memory Manager

Security checks across malware telemetry and agentic risk

Overview

This is a simple memory-management skill that clearly tells the agent how to read and write OpenClaw workspace memory, with no hidden code or install behavior.

Install this if you want agents to use durable workspace memory. Be aware that it may save preferences, decisions, or session context into MEMORY.md or daily memory notes; avoid asking it to store secrets or sensitive personal data unless you truly want that information persisted.

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
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs the agent to write persistent notes into workspace files like MEMORY.md and memory/YYYY-MM-DD.md, but it does not require a clear user-facing confirmation that files will be modified. In practice, this can lead to silent persistence of user data, preferences, or sensitive context, increasing privacy risk and creating opportunities for unintended durable state changes across sessions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.