AI电商专家｜小红书电商 图片视频全内容

• Outcome: Review
• Latest audit: Aug 23, 2026 · 9:56 AM UTC
• Version: 1.0.0

Overview

The skill matches its advertised IMIVA ecommerce workflow, but its helper runs a mutable npm package and gives that process the user’s full environment, which could expose unrelated secrets.

Install only if you are comfortable with an IMIVA token being used by a locally executed npm MCP package. Prefer running it in a clean shell or container with only the needed MCP_TOKEN, API_URL or IMIVA_API_URL, and PATH set, and consider pinning or reviewing the npm package version before use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

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: 85% 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: 91% confidence
• Finding: The skill documents use of shell commands, environment variables, and local file paths, but it does not declare corresponding permissions. This creates a trust and enforcement gap: a host may expose capabilities the user did not explicitly approve, enabling local file access, shell execution, or token handling beyond what the manifest signals.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The code launches an external npm package without any explicit warning to the user that third-party code will be downloaded and executed. In a skill context, this reduces informed consent and increases supply-chain risk because users may not realize that invoking the helper runs network-sourced code locally.

Missing User Warnings

Medium

• Confidence: 81% confidence
• Finding: The script passes `MCP_TOKEN` and API endpoint configuration into a subprocess that performs network-backed operations, but the code does not explicitly disclose that credentials will be used and sent to a remote service. This can surprise users and increases the risk of unintended credential exposure to the called package or remote endpoint.

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: 74% confidence
• Finding: os.environ.copy()

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.