ClawHub
Back to skill

Security audit

Money Router

Security checks for vulnerabilities and agentic risk

Overview

Money Router is a coherent finance-rate lookup skill that uses disclosed Coinnect API endpoints and does not show hidden execution, persistence, or credential access.

Before using verification or quest features, assume the provider, currency pair, observed rate, and fee you submit will be sent to Coinnect. Avoid adding personal account details or transaction identifiers unless the service explicitly asks for them and you are comfortable sharing them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill exposes a POST endpoint that sends user-supplied rate, provider, and currency data to an external service, but the documentation does not clearly warn users that this information leaves the local agent context. While the data is not highly sensitive by default, financial activity details and provider usage can still reveal user behavior and should be disclosed before submission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.