ClawHub
Back to skill

Security audit

momo

Security checks for vulnerabilities and agentic risk

Overview

Momo is a disclosed time-tracking and invoicing helper with a local script, and the inspected artifacts do not show hidden, persistent, network, credential, or destructive behavior.

Install only if you are comfortable with a skill that has local command execution permission. Treat it as an early/stub implementation: review generated invoices or reports before using them for client billing, and confirm any future version still limits file changes and external actions to what you intend.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The invocation guidance is overly broad: 'Invoke Momo when logging time, preparing reports, or generating client invoices' does not constrain when the skill should be selected or what prerequisites must be met. In an agent setting, ambiguous triggers can cause the skill to activate in loosely related contexts and run local executable scripts unnecessarily, increasing the chance of unintended actions or misuse.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The manifest requests the "exec" permission and declares a shell script for a skill whose stated purpose is time tracking, timesheets, invoicing, and payment tracking. That capability enables arbitrary command execution on the host, which is far more powerful than the business function described and materially increases the attack surface if the script or prompt flow is abused.

Static analysis

No suspicious patterns detected.