ClawHub
Back to skill

Security audit

KrumpKraft Play

Security checks for vulnerabilities and agentic risk

Overview

This is a benign instructional skill for a Minecraft economy, but users should be careful with payment commands because token transfers can be irreversible.

This skill can be installed as instructional documentation. Before using any payment command such as !pay, !usdc, !ip, or !jab, verify the agent ID, recipient 0x address, token, network, and amount, and consider a small test transfer first because blockchain payments are generally not reversible.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation explicitly teaches users how to invoke token transfer commands for USDC.k, $IP, and JAB but omits basic safety warnings such as verifying the destination address, double-checking the amount, and understanding that blockchain transfers are generally irreversible. In a skill centered on in-game payments and agent-driven transfers, this omission increases the likelihood of accidental loss, misdirected funds, or social engineering abuse through copied example commands.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.