Back to skill

Security audit

MuninnDB Integration for Hermes Agent

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local MuninnDB memory integration for Hermes, with expected credential and persistence considerations but no evidence of hidden, destructive, or unrelated behavior.

Install this only if you want Hermes to use MuninnDB as persistent memory. Keep the MuninnDB bearer key private, avoid storing secrets or untrusted instructions as reusable memory, and inspect the referenced snapshot cron script or related auto-memory skill before enabling periodic snapshots.

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

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.