ClawHub
Back to skill

Security audit

westin-hotel-booking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a hotel-search integration that makes disclosed network queries for Westin hotel prices, with some caution needed around its external proxy and broad trigger wording.

Install only if you are comfortable with hotel search terms, dates, destinations, and any configured PROXY_TOKEN being sent to the hardcoded external proxy. Prefer using it when you explicitly want Westin hotel search, pricing, details, or package links.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tainted flow: 'req' from os.environ.get (line 23, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/westin_hotel.py (reported line 33)May include surrounding context.

python
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")}

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill invokes a Python script that likely requires network access and may read environment configuration, but the manifest does not declare any tool scope or allowed-tools restrictions. This weakens sandboxing and reviewability, creating unnecessary privilege ambiguity and increasing the chance of unintended tool or data access if the skill runtime is permissive.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger condition activates on any mention of '威斯汀/Westin', which can cause the skill to run outside clear user intent to search or book hotels. Over-broad invocation can lead to unnecessary external queries, unintended disclosure of user context to third-party services, and confusing or unsafe tool use when the user is discussing the term in another context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.