AI电商专家｜抖音电商 图片视频全内容

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

Overview

This appears to be a legitimate IMIVA ecommerce content skill, but it needs Review because its helper runs an unpinned remote npm package and passes the full local environment to it.

Install only if you trust the IMIVA npm package and are comfortable sending product assets and task data to the IMIVA service. Prefer running it in an environment with only the needed MCP_TOKEN and API_URL set, and consider pinning the npm package version before use.

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: 89% 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 use of shell commands, environment variables, and local file paths, but it does not declare permissions or boundaries for those capabilities. That can cause the host agent to invoke file/system access implicitly, increasing the chance of unintended local file exposure, token mishandling, or unsafe command execution in environments that rely on declared permissions for policy enforcement.

Vague Triggers

Medium

• Confidence: 78% confidence
• Finding: The invocation description is extremely broad and overlaps with many generic ecommerce-content tasks, making accidental or over-frequent activation more likely. In agent systems, over-broad matching can route unrelated user requests into a skill that performs external tool actions and may consume credits or process sensitive business assets without sufficiently specific user intent.

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: 93% confidence
• Finding: os.environ.copy()

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.