ClawHub
Back to skill

Security audit

Crowded Trade Detector

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent paid crypto-signal integration, but it asks the agent to use a raw wallet private key for automatic paid requests without clear spending controls or per-call consent.

Review carefully before installing. Use only a dedicated low-balance wallet, never a primary wallet, and make sure your agent asks for confirmation before each paid call. Treat each invocation as a potential paid transaction on Base mainnet and monitor usage closely.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:25
Finding

Automatic Wallet Payment Authorization Without Explicit Spending Controls

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to make an x402-authenticated request using a locally available EVM private key and states that payment authorization is handled automatically, but it does not prominently warn that invoking the request can spend funds from a wallet. In an agent setting, this creates a real risk of unintended paid transactions or repeated charges, especially if the skill is triggered autonomously or by a user who does not understand that a funded wallet is required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.