AI电商专家｜Instagram INS 电商 图片视频全内容

• Outcome: Review
• Latest audit: Aug 23, 2026 · 9:49 AM UTC
• Version: 1.0.0

Overview

The skill matches its stated ecommerce-content purpose, but its helper runs an unpinned npm package and passes the whole local environment to it, which can expose unrelated secrets.

Review before installing. Use this only if you trust IMIVA and the @infimind npm package, and prefer pinning a reviewed package version. Run it from a clean environment that exposes only MCP_TOKEN, API_URL or IMIVA_API_URL, PATH, and required runtime variables, and confirm product assets, model choices, quantity, and credit limits 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 (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: 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: 93% confidence
• Finding: The skill instructs use of environment variables, local file paths, and shell commands, but it does not declare corresponding permissions or capability boundaries. This can mislead the host or user about what the skill can access, increasing the risk of unintended local file access, token exposure, or command execution in environments that rely on declared permissions for trust decisions.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The invocation guidance is extremely broad, covering many ecommerce and social-commerce workflows without clear trigger constraints or narrow task boundaries. Over-broad activation can cause the agent to invoke the skill in contexts the user did not intend, potentially sending sensitive product assets, local paths, or business data to external tooling unnecessarily.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The skill enables implicit invocation with no visible activation constraints, which can cause the agent to auto-select this skill in contexts the user did not clearly intend. In a commerce-content workflow that may trigger external tool use, content generation, or handling of business assets, this increases the risk of unintended actions, prompt-scope confusion, and accidental disclosure of merchant data or task parameters.

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: Launching a remote-resolved `npx` package without an explicit user warning reduces informed consent and can hide that unreviewed third-party code will be executed locally. In this skill context, users may expect a normal helper script, not an on-demand package fetch and execution path that can change over time.

Missing User Warnings

Medium

• Confidence: 79% confidence
• Finding: The script passes authentication material and tool arguments into an MCP process that then communicates with a remote API, but the CLI does not prominently disclose that network transmission will occur. This matters because tool arguments may contain sensitive business data, media paths, or tokens in an ecommerce workflow.

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

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.