AI电商专家｜电商图片视频全套生成

• Outcome: Review
• Latest audit: Aug 23, 2026 · 9:38 AM UTC
• Version: 1.0.0

Overview

The skill appears to support legitimate IMIVA ecommerce content generation, but it needs Review because it runs an unpinned external npm tool while passing it a broadly inherited local environment.

Review before installing. Use this only if you trust the IMIVA npm package and are comfortable sending selected product media and task data to the IMIVA service. Prefer a pinned package version and a minimal environment containing only needed variables such as PATH, MCP_TOKEN, and API_URL; avoid running it from shells that contain unrelated cloud, CI, or account secrets.

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: 86% 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 instructs users to run shell commands, read local files via $SKILL_PATH/scripts/imiva_mcp.py, and use environment variables such as MCP_TOKEN, but it does not declare corresponding permissions or capabilities. This creates a trust and review gap: a client or user may grant broader access than expected, and sensitive local data or secrets could be exposed through the undocumented file/system interactions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: Enabling implicit invocation without trigger constraints allows the platform to auto-select this skill in broader contexts than the user may have intended. Because this skill can initiate ecommerce content-generation workflows and tool usage, unexpected invocation could lead to unintended processing of user data, accidental task creation, or confusing cross-skill behavior.

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: 84% confidence
• Finding: os.environ.copy()

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.