ClawHub
Back to skill

Security audit

AI电商专家｜天猫 图片视频全内容

Security checks across malware telemetry and agentic risk

Overview

This ecommerce content skill is purpose-aligned, but it should be reviewed because it runs a mutable npm package and passes the caller's full environment to it.

Install only if you trust the IMIVA npm package and service with your product media, task data, and MCP token. Prefer pinning the npm package version, running it from a clean environment with only the required token and API URL, and confirming credits before creating paid tasks. Avoid running it from shells that contain unrelated cloud keys, repository tokens, or other sensitive environment variables.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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
95% 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 documents shell execution, file-path handling, and environment-variable use, but does not declare corresponding permissions. This creates a transparency and containment gap: a host or reviewer may underestimate the skill's access to local files and secrets, increasing the chance of unintended token exposure or unsafe local command execution in a trusted workflow.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
This script silently executes a remote npm package without any user-facing warning or confirmation. In a skill context, that is especially risky because operators may believe they are running local helper code while actually granting execution to code downloaded at runtime.

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
78% confidence
Finding
os.environ.copy()

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.