ClawHub
Back to skill

Security audit

AI电商专家｜Etsy 图片视频全内容

Security checks across malware telemetry and agentic risk

Overview

This skill mostly matches its ecommerce content purpose, but its helper runs an unpinned npm package with the full local environment, which can expose unrelated secrets if the package or its dependencies change or are compromised.

Review this before installing in any environment that contains cloud keys, CI tokens, production credentials, or sensitive business data. Prefer pinning the npm package version, running it with a minimal environment containing only the required token/API URL/PATH, and requiring explicit user confirmation before any task that uploads local media or spends credits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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
92% confidence
Finding
proc = subprocess.Popen( [npx, "-y", PACKAGE], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1,

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill enables implicit invocation with no visible activation constraints, so it may be triggered automatically in contexts where the user did not clearly request this ecommerce capability. Because this skill can drive content-generation workflows and references real MCP tooling, unintended invocation could cause unauthorized processing of user inputs, unexpected task creation, or privacy and cost issues.

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.