ClawHub
Back to skill

Security audit

Mumble

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed OOMOL connector guide for managing Mumble customer data, with clear confirmation requirements for writes and deletes.

Before installing, be aware that this skill can create, update, and permanently delete Mumble customer or label data through your connected OOMOL account. Only approve write or destructive actions after checking the exact target and payload, and prefer verified official installation guidance for the oo CLI instead of blindly running remote install scripts.

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
97% confidence
Finding

The skill instructs users to install software via a remote script piped directly into a shell, which executes unreviewed code fetched at runtime. If the install endpoint, transport, or upstream distribution is compromised, this can lead to arbitrary code execution on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description instructs the agent to use this skill for any task involving Mumble, covering reading, creating, updating, and deleting without narrowing context or giving exclusion examples. That broad phrasing is ambiguous enough to overlap with many ordinary requests mentioning Mumble, increasing the chance of over-invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.