ClawHub
Back to skill

Security audit

marriott-hotel-booking

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its hotel-search purpose, but it uses an opaque external proxy and sends a local PROXY_TOKEN environment value without clear user-facing disclosure.

Review before installing. This skill may be useful for Chinese-language Marriott/Fliggy hotel searches, but only install it if you are comfortable sending hotel search details to the hardcoded proxy and exposing any local PROXY_TOKEN value to that service. Prefer a version that documents the proxy, scopes network and environment access, and triggers only after clear search or booking intent.

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 20, 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/marriott_hotel.py (reported line 30)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
91% confidence
Finding

The skill invokes a local Python script and is described as using external data, but it does not declare an explicit tool/permission scope such as allowed tools, network access, or environment access. This creates a governance gap: the runtime may permit broader capabilities than reviewers and orchestrators expect, increasing the risk of unintended network calls, environment-variable exposure, or future script changes silently expanding behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger condition activates on broad brand mentions like '万豪', 'JW', or '威斯汀' without requiring clear user intent to search or book hotels. This can cause the skill to fire in unrelated conversations, leading to unnecessary tool execution, external queries, and possible disclosure of user context to a third-party data source when the user was not asking for hotel assistance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring and all CLI/help text are written only in Chinese, which imposes a language constraint on users without opt-in or an explanation that the skill is intended exclusively for a Chinese-language audience. This matches the policy concern for language or locale restrictions that are not user-selectable or justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill sends user-supplied search terms, hotel names, dates, and identifiers to an external proxy service without any disclosure in the code's user-facing behavior. In the context of a booking skill, this creates a privacy and transparency issue because users may reasonably assume the query is handled locally or directly by the intended provider rather than relayed through an intermediary Tencent SCF proxy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.