Back to skill

Security audit

W酒店查询与预订

Security checks across malware telemetry and agentic risk

Overview

The skill appears to perform W hotel searches, but it embeds a shared proxy token and sends travel queries through an environment-defined proxy, so it should be reviewed before use.

Install only if you are comfortable with your hotel search details being sent to the skill's proxy and downstream travel services. The code does not show destructive behavior or local data collection, but the embedded shared token and unconstrained proxy URL are security hygiene issues that should be fixed or clarified by the publisher.

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 (4)

Tainted flow: 'req' from os.environ.get (line 26, 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
94% confidence
Finding
resp = urllib.request.urlopen(req, timeout=timeout)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill advertises networked functionality and the data-flow section explicitly states that user query parameters are sent to an agent service and downstream travel platform APIs, yet no permissions are declared. This creates a transparency and governance gap: users and platform operators may not have clear visibility into external data access and execution capabilities, increasing the risk of undisclosed outbound data transmission or misuse.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill states that user inputs such as city, dates, and keywords are forwarded to an agent service and travel platform APIs, but it does not present a clear privacy warning or consent-oriented disclosure to the user. Even if the data seems low sensitivity, travel queries can reveal location plans and behavioral patterns, and third-party sharing without clear notice can create privacy, compliance, and trust risks.

Missing User Warnings

High
Confidence
98% confidence
Finding
The code reads a sensitive token from the environment but falls back to a hardcoded default token embedded in source. Embedded credentials are easily leaked through source distribution, logs, or reverse engineering, and if the default is active an attacker can reuse it to access the upstream proxy or impersonate this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.