ClawHub
Back to skill

Security audit

Ucp Checkout Mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent documentation for building checkout MCP tools, but it enables agent-driven purchases without clearly requiring human approval, spending limits, or other safeguards.

Review carefully before installing or using this skill in production. It should only be used with explicit user confirmation before purchase completion, test-mode defaults, spending limits, merchant/domain allowlists, clear credential handling, and audit logging for checkout actions.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
5. Implement idempotency on create and complete tools

**Connecting to an existing MCP server (e.g., Shopify):**
1. Authenticate (Shopify uses OAuth2 client_credentials for access tokens)
2. Connect to the MCP endpoint
3. Call tools with proper `_meta.ucp.profile` and checkout payloads
4. Parse tool results for checkout status and messages

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly promotes exposing checkout operations as MCP tools that AI agents can call to autonomously browse and purchase, but it does not warn users that this enables real-world financial transactions. In this context, omission of that warning is security-relevant because it increases the risk of unsafe deployment, over-permissioning, or accidental autonomous purchases without appropriate human approval controls.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
Shopify provides a production MCP server for UCP checkout. Before implementing:
- Fetch https://shopify.dev/docs/agents/checkout/mcp for the latest auth flow, endpoint URL format, and error codes
- Authentication uses `POST https://api.shopify.com/auth/access_token` with client credentials
- MCP endpoint is `POST https://{shop-domain}/api/ucp/mcp`

Static analysis

No suspicious patterns detected.