ClawHub
Back to skill

Security audit

Morrow Agent Memory

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for building persistent agent memory, with disclosed persistence and setup guidance that fits its purpose.

Install this if you want guidance for persistent agent memory. Review memory files periodically, avoid storing secrets or sensitive personal data in durable memory, protect any OpenClaw gateway token, and run the optional Graphiti/Neo4j setup only in an environment where persistent services and unpinned package installs are acceptable.

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 trigger text ends with a broad catch-all phrase covering 'any task involving durable state for AI agents,' which can cause the skill to activate for loosely related prompts well beyond its intended scope. Over-broad auto-activation increases the chance that memory-related instructions, assumptions, or tool guidance are injected into unrelated tasks, creating prompt-scope confusion and potentially influencing agent behavior in contexts where persistence or memory access is unnecessary.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.