Security audit

Profit Margin Calculator Shopify

Security checks for vulnerabilities and agentic risk

Overview

The skill presents itself as a Shopify/DTC calculator but actually runs an Amazon/FBA profit calculator, which could mislead users making business decisions.

Review this skill carefully before installing. It appears useful as a local Amazon/FBA margin calculator, but it should not be relied on for Shopify/DTC CAC, payment processing, 3PL, LTV/CAC, or DTC benchmark analysis unless the implementation or documentation is corrected. Prefer a pinned, project-local install if you choose to use it.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:14
Finding: Unpinned Third-Party CLI and Mutable Remote Skill Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: This is a clear description-behavior mismatch. The declared description says the skill is for Shopify/DTC sellers and specifically mentions CAC, payment processing fees, 3PL costs, LTV/CAC analysis, and DTC benchmarks. The code instead is explicitly labeled and implemented as an 'Amazon Profit Calculator' with Amazon referral fee tables and FBA fee concepts throughout. It calculates ad spend ratio and profitability, but not CAC or LTV/CAC. It also does not model payment processor fees or 3PL costs, and contains no Shopify-specific logic or benchmarks. The lack of API usage is consistent with the description, but the primary purpose and core capabilities are materially different.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill metadata says this is a Shopify/DTC profit margin calculator, but the implementation is explicitly Amazon/FBA-specific, including Amazon referral fee tables and FBA fulfillment/storage concepts. This mismatch can mislead users into making business decisions with the wrong cost model, causing materially incorrect outputs and eroding trust in the agent’s behavior.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The module docstring prominently advertises an Amazon Profit Calculator while the declared skill purpose is Shopify/DTC. This contradictory framing increases the likelihood of misuse, especially in autonomous or semi-automated agent workflows where metadata and code comments may be interpreted as authoritative guidance for routing and execution.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description claims Shopify/DTC-specific features such as LTV/CAC analysis and DTC benchmarks, but the code only performs product-level Amazon-style margin calculations and reporting. In an agent setting, this is dangerous because downstream users or systems may rely on absent analyses and assume outputs include customer acquisition and lifecycle economics when they do not.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.