AI电商专家｜16:9 电商 TVC 广告

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

Overview

The skill mostly matches an IMIVA ecommerce video workflow, but it gives a local agent broad npm/MCP execution with a token and more environment access than necessary.

Review before installing. Only use this if you trust the IMIVA service and the npm package with your MCP token and selected product media. Prefer pinning the npm package version and limiting the child-process environment to MCP_TOKEN and API_URL/IMIVA_API_URL. Confirm dryRun estimates and maxCredits before any paid task, and revoke the token if you stop using the skill.

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 (7)

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: 70% 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: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: L003 says 'Use this skill for IMIVA ecommerce content, product images, product detail pages, KOC seeding, product video, viral creative recreation, marketplace listing and social commerce workflows.' This reads like a very broad activation description covering many common ecommerce tasks, without explicit boundaries or negative examples, which could cause unintended invocation beyond the stated 16:9 TVC niche.

Natural-Language Policy Violations

Medium

• Confidence: 80% confidence
• Finding: The metadata fixes the language to 'zh-CN', and L054 further says it is especially suitable for Chinese users. This is a natural-language locale restriction without any stated opt-in or alternative language path, which may violate language/locale choice policy.

Natural-Language Policy Violations

Low

• Confidence: 95% confidence
• Finding: This Python file contains user-facing error messages entirely in Chinese when required runtime dependencies or tokens are missing. The policy for natural-language violations applies to all file types, and there is no opt-in or alternative locale handling shown for users who may expect another language.

Env Variable Harvesting

High

• Category: Data Exfiltration

Content

npx = shutil.which("npx")
    if not npx:
        raise SystemExit("未找到 npx。请先安装 Node.js 18 或更高版本。")
    token = os.environ.get("MCP_TOKEN", "").strip()
    if not token:
        raise SystemExit("缺少 MCP_TOKEN。请在 IMIVA 的 MCP Token 页面创建后通过环境变量提供。")
    return npx, token

• Confidence: 70% confidence
• Finding: os.environ.get("MCP_TOKEN

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: 60% confidence
• Finding: os.environ.copy()

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.