ClawHub
Back to skill

Security audit

mumo (Hermes Agent)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed multi-model review helper that sends user-provided prompts to mumo's MCP service, with no evidence of hidden execution, persistence, or data theft.

Install only if you are comfortable sending selected prompts, snippets, and review context to mumo and its model-provider panel. Avoid including secrets, credentials, private customer data, or proprietary details unless your organization has approved that data flow, and review/redact sessions before using any public sharing feature.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The description says mumo runs a panel of multiple named frontier models, but it does not prominently and explicitly warn that user prompts and possibly attached context may be transmitted to multiple third-party providers. In a security-sensitive workflow, this can lead users to share credentials, internal architecture, customer data, or regulated information under incomplete understanding of the data exposure path.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents a `share_session` capability as a normal tool action but does not explicitly warn that sharing can expose full deliberation content, prompts, attached context, and potentially sensitive architectural or security discussions. In this skill’s context, users are specifically encouraged to use the panel for high-risk topics like auth, payments, tokens, data exposure, and migrations, which increases the chance that a publicly shared session could leak sensitive internal information.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
README.md:52