Back to skill

Security audit

RelayShield MCP Proxy Firewall for MetaMask Agent Wallet

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it reports an unpinned installer command that can fetch changing package and repository content, and a mismatch between the stated wallet-screening purpose and the reported installation behavior.

Consider the suspicious verdict and the unpinned installer before installing, especially if the skill would be used alongside wallet tools. The scan was partial: it covered the bundled Markdown file but could not resolve two references, and it did not establish what downloaded skills contain. The findings do not establish malicious intent.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied command's direct purpose is skill installation, materially different from the declared screening entry point. Installation could support later screening, but this chunk contains no implementation or invocation of counterparty screening, payTo validation, or Firewall enforcement. The behavior of any downloaded skills cannot be established from this command alone.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

Although npx skills is an installer rather than an MCP server, the underlying supply-chain concern is valid: the command executes an unpinned package and installs skills from an unpinned repository reference. A compromised package release or repository update could introduce executable code or adversarial agent instructions into a wallet-enabled environment.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 200)May include surrounding context.

md
`mm transfer`. If the same address were clean, the screen would return LOW
/ proceed, the agent would run the transfer, and the human would still
approve it before anything moves. Through the proxy path, the same call is
blocked at the tool call and never reaches the MetaMask MCP server, so no
approval is ever issued for it.

## Pricing and how to get it

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 213)May include surrounding context.

md
self-hosted deployments on Vultr, DigitalOcean, and OpenNebula. The x402
pre-payment screens are pay-as-you-go instead: counterparty-screen $0.10
per call, pin-check $0.02 per call. Get started at
https://api.relayshield.net/developers, or email
support@relayshield.net.

## Limits, stated plainly

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The proposed installation command executes an unpinned skills package and retrieves the RelayShield skill without an immutable source reference. This permits future package or repository changes to alter what users install, with elevated sensitivity because the resulting instructions operate alongside wallet tools.

Content

No source excerpt is available for this finding.