Security audit

Shopify Auto Invoicing & Inventory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a review-first local Shopify reporting helper, but its CSV exports should be handled carefully because spreadsheet formula escaping is missing.

Install only if you are comfortable using it as a local, review-first helper for Shopify exports. Treat generated CSV files as untrusted business data: inspect inputs, avoid opening exports with formula execution enabled, and consider adding spreadsheet-safe escaping before using the scripts for customer-controlled order or product data.

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 (4)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/invoice_export.py:55
Finding: CSV Formula Injection in Invoice Exports
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/stock_sync.py:83
Finding: CSV Formula Injection in Stock Reconciliation Exports
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/monthly_ops_report.py:57
Finding: CSV Formula Injection Through SKU Values in Monthly Reports
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: scripts/monthly_ops_report.py:51
Finding: Malformed Quantity Causes Monthly Report Generation to Fail
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 89% confidence
Finding: The skill advertises broad Shopify workflow capabilities, but the described/bundled behavior appears limited to local file transformation and reporting helpers. This mismatch can mislead operators into trusting the skill to perform order detection, inventory reconciliation, or monthly reporting correctly when those controls may not actually exist, increasing the chance of incorrect financial or stock actions.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.