ClawHub
Back to skill

Security audit

Komari

Security checks for vulnerabilities and agentic risk

Overview

This Komari administration skill is mostly coherent, but it includes high-impact Komari actions and unsafe one-line installer instructions that users should review before installing.

Install only if you trust OOMOL and need agent-driven Komari administration. Before using it, avoid automatic CLI installation from the piped installer, prefer the official install guide with verification where possible, and require explicit approval for destructive actions, secret-returning reads, provider/settings changes, and remote command execution.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
95% confidence
Finding

The skill instructs use of a remote-install pattern that pipes a network-fetched script directly into a shell (curl ... | bash). If an agent follows this guidance, it could execute unverified code from an external source, enabling supply-chain compromise or arbitrary code execution on the host.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description says to use this skill for ANY Komari request, including read, write, and delete operations, which creates an overly broad routing trigger. This can cause the agent to invoke a highly privileged skill for loosely related requests and increases the chance of unintended access to sensitive data or execution of destructive Komari actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.