ClawHub
Back to skill

Security audit

Hotwallet

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malware, but it is a hotwallet/blockchain reference tool whose actual content is generic placeholder guidance that could mislead users in a financial security context.

Review this skill carefully before installing. It appears safe from a system-security perspective, but do not rely on it for hotwallet design, custody, compliance, incident response, or transaction-security decisions unless the publisher replaces the placeholder material with accurate domain-specific guidance.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script is presented as a blockchain hotwallet reference tool, but it only emits generic placeholder-style finance and compliance text that is not specific to hotwallet operations. In a security-sensitive domain like blockchain wallets, this mismatch can mislead users or downstream agents into trusting irrelevant or inaccurate guidance, increasing the risk of unsafe operational decisions.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The inline documentation and command descriptions claim a hotwallet reference tool, but the output content is largely boilerplate and not meaningfully tied to hotwallet concepts. This is dangerous because users may rely on the tool for wallet-related guidance in a high-risk context, where misleading documentation can cause configuration, custody, or compliance mistakes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.