Back to skill

Security audit

MuninnDB Integration for Hermes Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed local MuninnDB/Hermes integration guidance and small local setup checks, with no evidence of hidden exfiltration, destructive behavior, or deceptive instructions.

Before installing, verify that you want Hermes connected to a local MuninnDB service and review any separate cron-based memory snapshot workflow before enabling it, especially because periodic memory capture can persist beyond a single session.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill documents shell-capable behavior such as a cron-driven snapshot script under ~/.hermes/scripts, but it declares no explicit tool scope or permissions boundary. In an agent ecosystem, undocumented shell capability increases the chance that the skill can trigger or imply local command execution without clear user visibility or policy enforcement.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition, 'Use when user wants to configure MuninnDB,' is broad and underspecified, so an agent may activate the skill in loosely related contexts and apply configuration guidance or operational steps without sufficiently clear user intent. Over-broad activation raises the risk of unintended system changes, especially here because the skill includes local service endpoints, authentication guidance, and cron-based automation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Several operational instructions are written in German, including setup guidance and warnings, without stating that the skill is German-only or offering a language/locale option. This can violate language/locale policy expectations when users are not given opt-in or an explicitly documented regional constraint.

Content

No source excerpt is available for this finding.