Uniswap Scan Opportunities

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 4:48 PM UTC
• Version: 0.1.0

Overview

This skill is a disclosed Uniswap opportunity-scanning helper, but users should treat its financial outputs as research and be careful with the unpinned install commands.

Install through a trusted, reviewed ClawHub flow when possible, avoid running unpinned npx commands with elevated privileges, and verify the source before using README install commands. Treat scan results as leads for further research, not guaranteed returns or personalized financial advice.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: README.md:7

Finding

Unpinned Third-Party Installers and Mutable Sources Permit Supply-Chain Code Execution

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 96% confidence

Finding

The README instructs users to run npx skills add without pinning a specific package version, which means the installer will fetch the latest published code at execution time. If the upstream package is compromised, maliciously updated, or subject to a dependency-chain attack, users could execute unreviewed code on their system during installation.

Content

No source excerpt is available for this finding.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 97% confidence

Finding

The command npx clawhub@latest install scan-opportunities explicitly tracks the latest version, causing users to execute whatever code is current in the registry at install time. This increases supply-chain risk because a malicious release, account compromise, or typo/dependency attack could turn the installation step into arbitrary code execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The description uses broad phrases like 'best opportunities' and 'high-yield pools,' which can cause the skill to activate on general investment questions outside a narrowly intended scanning workflow. Over-broad invocation increases the chance the agent routes users into financial-opportunity recommendations without sufficient gating, context checks, or clearer user intent confirmation.

Content

No source excerpt is available for this finding.

External Model or Provider Selection

Medium

• Category: Excessive Agency
• Confidence: 90% confidence

Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

md

---
name: scan-opportunities
description: Scan for LP opportunities, arbitrage, and high-yield pools across all Uniswap deployments. Use when the user asks about the best opportunities, high-yield pools, or arbitrage.
model: opus
allowed-tools: [Task(subagent_type:opportunity-scanner)]
---

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The trigger examples are vague and open-ended, such as 'Where should I LP?' and 'What are the best opportunities right now?', without boundaries or disambiguation rules. This makes invocation overly permissive and can cause the skill to handle broad portfolio or investment-advice requests that may exceed the intended scope of a market-scanning tool.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.