ClawHub
Back to skill

Security audit

Wallet Choice Advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only wallet setup advice skill with no evidence of file access, wallet integration, persistence, or hidden execution.

Before installing, treat this as general wallet setup guidance rather than financial advice. Avoid sharing seed phrases, private keys, exact balances, account logins, or recovery material with the agent; the inspected artifact does not request or access them.

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 (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description is for a wallet recommendation helper with no code-side capabilities beyond prompt-based guidance. The actual code chunk does not implement or exercise wallet recommendation behavior at all; instead, it tests security behavior of a handler when given a suspicious skill_name, specifically ensuring the handler does not read local files. This is a materially different primary purpose and capability from the declared skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.