ClawHub
Back to skill

Security audit

Minecraft

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only Minecraft helper with optional, disclosed local notes and no automatic downloads, network use, credentials, or executable code.

Install this if you want Minecraft-specific help that can remember edition, play style, and recurring build or server context. During setup, only allow persistence if you want those notes saved under ~/minecraft/, and avoid storing server tokens, paid account details, or other sensitive data.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file says the skill should learn to activate whenever the user mentions broad topics like worlds, builds, farms, or server setup. These topics are common within Minecraft conversations and the instructions do not provide exclusion conditions or negative examples, making the activation scope ambiguous and potentially overbroad.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.