ClawHub
Back to skill

Security audit

The Graph MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently helps agents use The Graph's MCP endpoint through uxc, with expected API-key and command-link setup for that purpose.

Before installing, understand that this skill will guide your agent to store or reference a The Graph API key in uxc, create a scoped auth binding, and create a local linked command named thegraph-mcp-cli. Review those local uxc entries if you later uninstall or rotate credentials.

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
97% confidence
Finding
There is a clear description-behavior mismatch. The declared purpose presents an operational skill for interacting with The Graph Subgraph MCP through UXC, including discovery and query workflows. The actual code chunk is a repository validation script that uses ripgrep and file checks to enforce documentation and configuration requirements for that skill. While the checked strings are related to the declared skill, the script itself does not implement the described runtime functionality; it only validates that accompanying docs mention it correctly.

Static analysis

No suspicious patterns detected.