ClawHub
Back to skill

Security audit

AI电商专家｜微信小店与视频号 图片视频全内容

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent for IMIVA ecommerce content generation, but it runs an unpinned remote npm tool with the user's token and full environment, which needs review before installation.

Review this before installing. Use a token with the minimum IMIVA permissions available, run it from a clean shell without unrelated cloud or CI secrets, and prefer pinning the npm package version or restricting the subprocess environment before use. Confirm credits and `maxCredits` before creating paid tasks, and only provide local media files you intend to upload to IMIVA.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

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
93% confidence
Finding
proc = subprocess.Popen( [npx, "-y", PACKAGE], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1,

Missing User Warnings

Medium
Confidence
96% confidence
Finding
Executing a remote npm package without any user warning or confirmation is dangerous because users may not realize the script is downloading and running third-party code on their machine. In this skill context, the package is granted access to MCP credentials and a copied environment, so silent execution materially increases compromise impact.

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
90% confidence
Finding
os.environ.copy()

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.