AI电商专家｜电商信息图套装

• Outcome: Review
• Latest audit: Aug 23, 2026 · 9:37 AM UTC
• Version: 1.0.0

Overview

The skill mostly matches an ecommerce image-generation purpose, but it runs a live external MCP package with broad environment access and broader activation scope than its core task needs.

Review before installing. Use this only if you trust the IMIVA npm package and are comfortable with token-backed external content generation. Prefer a pinned package version and a minimal environment containing only MCP_TOKEN, API_URL, and required runtime PATH values, and confirm credits before creating tasks.

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 (4)

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: 90% 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 consume environment variables for MCP_TOKEN/API configuration, but it does not declare these capabilities or permissions explicitly. This creates a transparency and consent problem: an agent or user may invoke the skill without realizing it can access local material and secrets needed to submit external tasks, increasing the chance of unintended data exposure or over-broad execution.

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The invocation text is much broader than the narrowly described 'ecommerce infographic set' use case, covering product images, detail pages, KOC seeding, viral creative recreation, marketplace listing, and social commerce workflows. Overly broad routing can cause the skill to activate in unrelated or higher-risk contexts, increasing the chance it processes sensitive assets, triggers paid external actions, or performs content-generation tasks the user did not specifically intend.

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: 92% confidence
• Finding: os.environ.copy()

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.