AI电商专家｜电商商品详情页

• Outcome: Review
• Latest audit: Aug 23, 2026 · 9:48 AM UTC
• Version: 1.0.0

Overview

This skill does the advertised ecommerce generation work, but it runs a mutable external npm MCP package with inherited environment secrets, which warrants careful review before installation.

Install only if you trust the IMIVA service and the npm package maintainers. Prefer pinning @infimind/ecom-content-cli to a reviewed version, use a dedicated low-scope MCP token, run it in a clean environment without unrelated cloud or repository secrets, and provide only product media paths you intend to upload to IMIVA.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

env = os.environ.copy()
    env["MCP_TOKEN"] = token
    env["API_URL"] = os.environ.get("IMIVA_API_URL", os.environ.get("API_URL", DEFAULT_API_URL))
    proc = subprocess.Popen(
        [npx, "-y", PACKAGE],
        stdin=subprocess.PIPE,
        stdout=subprocess.PIPE,

• Confidence: 91% confidence
• Finding: proc = subprocess.Popen( [npx, "-y", PACKAGE], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1,

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill instructs users to run shell commands, read local files via paths, and use environment variables for secrets, but it does not declare corresponding permissions. This creates a capability/permission mismatch that can undermine user consent and platform policy enforcement, especially because the workflow handles local paths and tokens.

Vague Triggers

Medium

• Confidence: 77% confidence
• Finding: The description contains broad English invocation text covering many ecommerce and social-commerce workflows beyond the narrowly named skill purpose of product detail pages. Over-broad triggers can cause the skill to activate in unrelated contexts, increasing the chance that it handles prompts, files, or tool calls the user did not intend for this specific workflow.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The code reads a sensitive `MCP_TOKEN` from the environment and later forwards it to a subprocess without any user-visible notice or trust boundary warning. By itself this is common integration behavior, but combined with runtime execution of an external Node package it increases the chance that the credential is exposed to code the operator did not explicitly audit or approve.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: This code performs runtime external package execution via `npx`, which may download and run code from the network, yet provides no explicit warning to the user. That creates a supply-chain and transparency risk: operators may believe they are running a local helper while actually executing remote package code with access to credentials and business data.

Env Variable Harvesting

High

• Category: Data Exfiltration

Content

def invoke(method: str, params: dict | None = None) -> dict:
    npx, token = require_runtime()
    env = os.environ.copy()
    env["MCP_TOKEN"] = token
    env["API_URL"] = os.environ.get("IMIVA_API_URL", os.environ.get("API_URL", DEFAULT_API_URL))
    proc = subprocess.Popen(

• Confidence: 80% confidence
• Finding: os.environ.copy()

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.