ClawHub
Back to skill

Security audit

Mem

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Mem connector that can read and change notes, with clear user-confirmation requirements for writes and destructive actions.

Before installing, understand that this skill can access and modify your Mem notes through your OOMOL connection. Reads may run directly, but the skill instructs the agent to confirm exact payloads for writes and get explicit approval before destructive actions like trashing or deleting notes.

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
94% confidence
Finding
The description says to use this skill for ANY Mem request and instead of calling the API directly, which creates an overly broad auto-invocation trigger. That can cause the agent to route unrelated or sensitive Mem-adjacent tasks through a powerful connector skill, increasing the chance of unintended data access or state-changing operations being selected without sufficiently narrow task matching.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.