ClawHub
Back to skill

Security audit

Galleon DeFi Infra

Security checks for vulnerabilities and agentic risk

Overview

This skill discusses DeFi wallets, payments, and provider setup, but it frames them as scoped, user-authorized infrastructure checks rather than hidden financial actions.

Install this only for DeFi infrastructure readiness work, and review any provider login, wallet session, MCP allowlist, or payment setup before approving it. Treat successful connection tests as read-only readiness, not permission to trade, transfer funds, sign messages, or pay for APIs.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill’s stated role is infrastructure onboarding and diagnostics, but the content reaches into managed wallets, payment permissions, authenticated sessions, and signer-related capability handling. This broader operational scope can lead an orchestrating agent or user to invoke it in higher-risk contexts than expected, potentially enabling wallet/session changes or payment-authority workflows under a diagnostic label.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill describes actions that may require network and shell-backed diagnostics, but it does not declare any explicit tool scope such as allowed tools or permissions. That creates ambiguous execution boundaries: a host agent may expose broader capabilities than the author intended, increasing the chance of over-privileged use during setup, diagnostics, or wallet-related workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.