ClawHub
Back to skill

Security audit

Mem0 Memory Setup

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate setup guide for connecting Hermes to Mem0, but users should handle the API key and cloud memory behavior carefully.

Install only if you intend Hermes to use Mem0 cloud memory. Avoid pasting the API key into chat or logs, restrict permissions on ~/.mem0/config.json and ~/.hermes/.env, do not commit those files, and review the npm prefix/PATH changes before applying them.

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
88% confidence
Finding
The trigger phrases are broad and loosely bounded, so the skill may activate in conversations that merely mention memory, providers, or persistence without the user intending installation or credential setup. In this skill's context, accidental invocation is meaningful because it can steer the agent into package installation, account initialization, and configuration changes that affect the local environment and external services.

Missing User Warnings

High
Confidence
96% confidence
Finding
The document instructs the user to extract an API key from a local config file and append it into ~/.hermes/.env without strong warnings about shell history exposure, file permission risks, log leakage, or safer secret-handling practices. Because this skill is specifically about integrating a cloud memory provider, the credential directly enables access to stored memory data and service operations, so weak guidance around persistence and handling materially increases the chance of secret disclosure.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.