ClawHub
Back to skill

Security audit

Minecraft Wiki

Security checks for vulnerabilities and agentic risk

Overview

This is a simple offline Minecraft Java Edition reference skill with minor scope and reliability caveats but no evident harmful behavior.

Installers should treat this as a Minecraft Java Edition reference skill. It appears safe from a security standpoint, but users should specify Bedrock or another version when needed because the skill defaults to Java Edition 1.21.x.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to 'always use this skill' for essentially any Minecraft knowledge query, which is broader than a tightly scoped invocation rule. This can cause unnecessary routing to the skill, reduce user choice, and override better handling for ambiguous or cross-edition questions, but it does not itself introduce code execution, data exfiltration, or direct privilege abuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill hard-codes Java Edition assumptions and even includes a checklist to verify answers are Java-specific, without requiring confirmation that the user is asking about Java Edition. This can lead to confidently wrong guidance for Bedrock users, especially for mechanics, spawning, redstone, commands, or version-specific behavior, creating reliability and trust issues rather than a classic security compromise.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.