Back to skill

Security audit

Uniswap Research Token

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Uniswap token-research helper with no bundled executable code, but its installation instructions use mutable remote sources that users should treat carefully.

Before installing, prefer a pinned commit or reviewed package version instead of the README's mutable npx examples. Also treat the output as Uniswap liquidity due diligence only, not investment advice or a complete scam assessment.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
README.md:9
Finding
Unpinned Third-Party Installation Sources Create Supply-Chain Risk## Vulnerability Details **File Location**: `README.md`, lines 9–19 **Vulnerability Type**: Unpinned and mutable third-party installation sources **Risk Level**: Medium ### Vulnerable Code ```markdown Install into Claude Code or Cursor with: ```bash npx skills add https://github.com/wpank/Agentic-Uniswap/tree/main/.ai/skills/research-token ``` Or via Clawhub: ```bash npx clawhub@latest install research-token ``` ``` ### Technical Analysis The documented installation procedure instructs users to retrieve and execute third-party npm tooling through `npx`. The Clawhub command explicitly selects the mutable `latest` package version, while the GitHub installation source refers to the mutable `main` branch rather than a reviewed commit. Consequently, the code and Skill content installed by these commands can change after this audit without any corresponding modification to the audited repository. No version pin, commit hash, checksum, or signature is provided to ensure that users receive the reviewed content. This is a supply-chain weakness rather than evidence that the current upstream packages are malicious. Exploitation would require an attacker to compromise an upstream package, publisher account, registry distribution path, repository, or future release. ### Attack Path 1. An attacker compromises the upstream npm publisher, package, GitHub repository, or another relevant distribution component. 2. The attacker publishes a malicious package version under the mutable `latest` tag or modifies content reachable through the GitHub `main` branch. 3. A user follows the installation instructions in `README.md`. 4. `npx` downloads and executes the current third-party installer with the user's local privileges. 5. The compromised installer or remote Skill content executes malicious behavior or installs altered instructions into the user's agent environment. ### Impact Assessment Successful exploitation could ...[truncated 582 chars]
Remediation
## Remediation Suggestions 1. Replace `clawhub@latest` with an exact, reviewed package version. 2. Pin the GitHub source to an immutable commit hash instead of the `main` branch. 3. Provide cryptographic checksums or signed release artifacts and document how users should verify them before installation. 4. Identify the expected package publisher and repository ownership so users can validate the source. 5. Review installation scripts and transitive dependencies before updating pinned versions. 6. Where supported, use lockfiles, package integrity metadata, and a trusted dependency mirror. 7. Recommend installation under a least-privileged account or isolated environment and warn users not to run the commands with elevated privileges.
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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding
The README instructs users to run `npx skills add` against a remote GitHub URL without pinning an immutable version or commit. This allows the fetched package/tooling or referenced remote content to change over time, creating a supply-chain risk where a compromised upstream package or modified repository state could cause users to execute unexpected code during installation.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding
The command `npx clawhub@latest install research-token` explicitly tracks the latest published version, so users execute whatever code is current at install time rather than a reviewed, fixed version. If the package publisher account or package supply chain is compromised, or a malicious update is published, this README would direct users to run attacker-controlled code.

External Model or Provider Selection

Medium
Category
Excessive Agency
Content
---
name: research-token
description: Research a token's Uniswap liquidity, volume profile, pool distribution, and risk factors. Use when the user asks about a token's tradability, liquidity depth, or wants due diligence.
model: opus
allowed-tools: [Task(subagent_type:token-analyst)]
---
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.

Vague Triggers

Low
Confidence
88% confidence
Finding
This markdown file defines invocation guidance, so vague-trigger review applies. Phrases like "Due diligence on this token" and "Is X safe to trade?" are broad and lack explicit exclusion conditions, which could cause the skill to activate on generic trading-safety questions not necessarily limited to Uniswap liquidity research.

Static analysis

No suspicious patterns detected.