ClawHub
Back to skill

Security audit

sheraton-hotel-booking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Sheraton hotel lookup tool, but users should know their hotel search details and a proxy token may be sent to a fixed external proxy service.

Install this only if you are comfortable with hotel search inputs such as destination, dates, hotel names, and review keywords being sent to the fixed fliggy-proxy service. Configure PROXY_TOKEN only for that service, and avoid invoking the skill for casual Sheraton mentions unless you actually want a hotel lookup.

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 24, 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/sheraton_hotel.py (reported line 34)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
86% confidence
Finding

The skill invokes a local Python script that likely requires network access and possibly environment access, but the manifest does not declare any explicit tool scope or allowed-tools constraints. This creates unnecessary ambiguity about what the skill is permitted to do, increasing the risk of over-privileged execution or unintended access if the runtime grants broader capabilities than required.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition activates whenever a user mentions '喜来登/Sheraton', even if the user is discussing news, brand comparisons, complaints, or unrelated context rather than requesting a hotel lookup. This can cause unintended tool execution and unnecessary transmission of user-provided location or travel details to external data sources, which is especially risky in a booking/search skill connected to live network-backed data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

User-facing descriptions, return strings, usage text, and outputs are written entirely in Chinese, with no indication that other languages are supported or that the Chinese-only behavior is optional. This can violate language or locale policy when a skill imposes a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The _request function sends request bodies built from user inputs such as destination, hotel name, and review keywords to an external proxy service, and also includes the PROXY_TOKEN header. While the module docstring mentions the data source, the executable code provides no runtime notice, confirmation, or explicit disclosure to users that their query data is being sent to a remote third-party endpoint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.