ClawHub
Back to skill

Security audit

Vivid: Open Business Account

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Vivid business-account onboarding helper that sends confirmed legal-entity fields to Vivid to create a prefilled onboarding link.

Before installing, understand that confirmed legal-entity onboarding details will be sent to Vivid's remote MCP service to create an onboarding session. Check the confirmation summary carefully, especially country and entity type, and do not provide passwords, API keys, bank account numbers, or raw document contents in chat.

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 (3)

External Transmission

Medium
Category
Data Exfiltration
Content
| Property | Value |
|----------|-------|
| **Endpoint** | `https://api.prime.vivid.money/mcp` |
| **Transport** | Streamable HTTP (remote) |
| **Tool** | `build_onboarding_link` |
| **Auth** | None — the endpoint is publicly accessible. The tool only generates a pre-filled onboarding link; it does not create a bank account, access financial data, or perform any privileged operation. Identity verification happens later in the Vivid app. |
Confidence
76% confidence
Finding
The skill sends structured legal entity data to a remote third-party MCP endpoint over HTTP-based transport. Even though the description limits the operation to link generation, this is still an external transmission of potentially sensitive business and personal data to a publicly accessible unauthenticated service, creating privacy, compliance, and trust-boundary risks.

External Transmission

Medium
Category
Data Exfiltration
Content
"mcpServers": {
    "vivid-mcp": {
      "type": "http",
      "url": "https://api.prime.vivid.money/mcp"
    }
  }
}
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The flow specifies a default country of Germany if the user does not provide one, which can cause the skill to prefill regulated onboarding data without explicit user confirmation of that field. In a financial onboarding context, silently defaulting jurisdiction-related information can lead to incorrect submissions, user confusion, or accidental transmission of inaccurate personal/business data.

Static analysis

No suspicious patterns detected.