ClawHub
Back to skill

Security audit

威斯汀酒店查询与预订

Security checks across malware telemetry and agentic risk

Overview

This skill is a hotel search helper that sends user-entered hotel queries to a disclosed cloud proxy and does not show evidence of hidden local access, persistence, destructive actions, or data theft.

Install only if you are comfortable with hotel search terms being sent to the publisher's cloud proxy and downstream travel APIs. Avoid entering sensitive personal details in search keywords, and prefer a version that validates the proxy endpoint and removes the hardcoded fallback token.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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 (3)

Tainted flow: 'req' from os.environ.get (line 25, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
method="POST",
    )
    try:
        resp = urllib.request.urlopen(req, timeout=timeout)
        data = json.loads(resp.read().decode("utf-8"))
        if data.get("status") == "error":
            return {"success": False, "error": data.get("message", "未知错误")}
Confidence
97% confidence
Finding
resp = urllib.request.urlopen(req, timeout=timeout)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill advertises zero-configuration use and documents a cloud proxy plus travel-platform API access, yet no explicit permissions are declared despite network-capable behavior being implied. This creates a transparency and governance gap: users and platform reviewers may not understand that user queries are transmitted off-platform, which can lead to unintended data exposure and weak permission enforcement.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
# ===== 代理配置 =====
PROXY_URL = os.environ.get("PROXY_URL", "")
PROXY_TOKEN = os.environ.get("PROXY_TOKEN", "tp_8k2mX9vQ4z")


def _request(api_type, params, timeout=30):
Confidence
91% confidence
Finding
os.environ.get("PROXY_TOKEN

VirusTotal

51/51 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.