ClawHub
Back to skill

Security audit

ritz-carlton-hotel-booking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned Ritz-Carlton hotel search helper that calls a disclosed hotel data proxy and does not show persistence, deception, or destructive behavior.

Install this only if you are comfortable with hotel search terms, destinations, dates, hotel names, and optional review keywords being sent to the configured external proxy service to retrieve live results. Review ambiguous prompts before letting the agent invoke the skill when the user only says “丽思.”

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (5)

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/ritz_carlton_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
88% confidence
Finding

The skill invokes a Python script that likely requires network access and may access environment variables, but the manifest does not declare any explicit tool scope or permissions boundaries. This creates an authorization and review gap: the agent may run code with broader capabilities than users or platform policy expect, increasing the risk of unintended data access or outbound requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Using the overly broad trigger term “丽思” can cause the skill to activate for unrelated user requests, leading to incorrect tool execution and unnecessary transmission of user-supplied travel queries to external services. While this is not direct code execution, it expands the skill's activation surface and can cause privacy and integrity issues through accidental invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill forwards user-provided hotel search terms, destination names, hotel names, and review keywords to a third-party proxy service, but the code contains no user-facing disclosure, consent, or minimization. In a booking context this can expose travel intent and location-related personal data to an external operator, increasing privacy and compliance risk even if transport is HTTPS.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module description, function docstrings, CLI help text, and all returned user-facing strings are Chinese-only, which imposes a language constraint on users. There is no opt-in, alternative locale support, or documented justification that this is a China-specific or Chinese-only skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.