ClawHub
Back to skill

Security audit

Binance Meme Rush

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward public market-data CLI for meme-token feeds, with disclosed Binance Web3 API calls and no persistence or credential handling.

Before installing, understand that the skill will run a local Node script that sends your chosen filter parameters to Binance Web3 public API endpoints and returns live crypto market data. Do not treat results as financial advice.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill documents a network-capable CLI that calls upstream APIs, but the manifest does not declare any tool scope such as permissions or allowed-tools. That creates a policy gap: an agent or runtime may permit broader network access than reviewers and users expect, reducing transparency and weakening least-privilege controls.

Static analysis

No suspicious patterns detected.