ClawHub
Back to skill

Security audit

The Graph Token MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented helper for using The Graph Token API MCP through UXC, with its credential and link setup disclosed.

Before installing, understand that using this skill means configuring UXC with a The Graph Token API JWT and sending requested token or wallet queries to The Graph's MCP endpoint. Keep that JWT separate from other The Graph credentials and review the UXC auth binding if you later want to remove or rotate access.

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
98% confidence
Finding
The declared description presents the skill as an operational interface for querying The Graph Token API through UXC. However, the supplied code does not call the API, inspect MCP tools, retrieve token or wallet data, or perform JWT-authenticated requests. Instead, it validates that documentation and config files contain specific strings and setup instructions. This is a materially different primary purpose: QA/packaging validation for the skill docs/config, not execution of the skill’s advertised Token API functionality. Therefore the description does not accurately represent what this code chunk actually does.

Static analysis

No suspicious patterns detected.