Back to skill

Security audit

lann-booking

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly fits a massage booking assistant, but its setup and test helpers can run unpinned code and submit or log live booking data, so it needs review before installation.

Install only if you trust the Lann MCP server package/source and are comfortable sending booking details, including a mobile number, to open.lannlife.com. Avoid running the included test scripts against real data or production endpoints, and prefer a pinned, reviewed MCP server version or remote endpoint with explicit confirmation before bookings.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
scripts/start_mcp.sh:88
Finding

Unpinned MCP Package Is Automatically Downloaded and Executed

Content
View full analysis
mcp-config.json <
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/test_booking.py:76
Finding

Test Scripts Submit Real Production Bookings and Log Unmasked Phone Numbers

Content
View full analysis
&1) ``` ### Technical Analysis Both advertised test scripts target `https://open.lannlife.com/mcp/book/create`, which is presented throughout the project as the production booking endpoint. The test suites issue valid booking requests, not merely validation or read-only requests. The Python suite creates a valid default booking and then attempts b ...[truncated 2139 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (21)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

声明描述的是面向终端用户的业务能力:查询门店、查询服务、进行预约。实际代码仅是运维/开发辅助脚本,负责显示帮助、检查 Node.js/npm、提示如何获取 lann-mcp-server、启动 stdio/HTTP 模式,以及生成 mcp-config.json 配置。代码中虽然出现 API_ENDPOINT 和 booking 相关命名,但并没有真正执行门店查询、服务查询或预约请求,也没有处理城市、门店、服务项目、时间段等业务数据。因此代码的实际用途与声明的核心能力存在明显不一致,属于实质性描述-行为不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

声明描述的是一个可供用户使用的综合技能,支持门店查询、服务查询和在线预约。但提供的代码仅是“预约 API 测试脚本”,用于构造测试数据并调用 create 接口验证不同输入场景。它没有任何查询门店列表、查询服务列表、覆盖多城市检索等实现,也没有体现完整技能触发或交互逻辑。虽然代码与“在线预约”这一部分相关,但其主要行为是接口测试而不是实现声明中的完整功能,因此存在明显描述与行为不一致。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

声明描述的是一个提供门店查询、服务查询和在线预约的业务技能;但实际代码仅是一个用于测试预约创建 API 的 Shell 脚本。它构造测试数据并发起多个预约创建请求,覆盖正常与异常情况,属于开发/测试用途。虽然其中确实涉及“在线预约”相关接口,但没有实现任何门店查询或服务查询能力,且其核心行为是接口测试而不是向终端用户提供完整预约服务。因此描述与实际行为存在实质性不匹配。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document is written almost entirely in Chinese and all user interaction examples assume Chinese-language use, but it does not state that the skill is region-specific or offer users a choice of language/locale. This can violate language/locale policy requirements when a skill constrains interaction language without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 145)May include surrounding context.

方式 2:直接调用 API

使用 curl 或其他 HTTP 客户端直接调用预约接口:

bash
curl -X POST "https://open.lannlife.com/mcp/book/create" \

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger keywords include very broad everyday terms such as ‘服务’, ‘预约’, and ‘门店’, which can cause the skill to activate in unrelated conversations. In a skill that can collect phone numbers and initiate bookings, false activation increases the risk of unintended data collection, confused-deputy behavior, or accidental reservation attempts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

文档要求 mobile 必须匹配中国大陆手机号格式,但未明确说明该技能仅面向中国大陆用户,或为其他地区用户提供替代方式。这属于对语言/区域规则的隐含强制限制,可能与要求避免未经用户选择的 locale 约束相冲突。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill file defines all user-facing templates exclusively in Chinese, including fixed reply options and help prompts, with no indication that the user can choose another language. This is a natural-language policy concern because it imposes a specific language by default rather than offering opt-in or documenting a justified regional limitation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/api_reference.md (reported line 30)May include surrounding context.

请求示例

bash
curl -X POST "https://open.lannlife.com/mcp/book/create" \
  -H "Content-Type: application/json" \
  -d '{
    "mobile": "13812345678",

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This shell script presents its usage, modes, and operational messages only in Chinese, which effectively forces a specific language for users. The policy for this category requires flagging language or locale constraints when the skill does not offer a language choice or document a justified regional restriction.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The script sends booking data, including a phone number and appointment details, to an external endpoint and also prints the full payload locally. While this is expected for an API test client, it still creates a real data-exposure risk if real customer data is used, logs are retained, or the endpoint is changed/misconfigured, because personally identifiable information is transmitted and echoed without masking or environment safeguards.

Content

Scanner excerpt · scripts/test_booking.py (reported line 86)May include surrounding context.

python
print(json.dumps(payload, indent=2, ensure_ascii=False))

    try:
        response = requests.post(
            API_ENDPOINT,
            headers=HEADERS,
            json=payload,

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This second call site also transmits booking-related data to the external API without additional safeguards, in this case for a missing-parameters test. Even though the payload is partial, it still includes a phone number and store information, and the script prints and sends that data directly, which can expose PII or trigger unintended actions against a live service.

Content

Scanner excerpt · scripts/test_booking.py (reported line 197)May include surrounding context.

python
print(json.dumps(payload, indent=2, ensure_ascii=False))

    try:
        response = requests.post(
            API_ENDPOINT,
            headers=HEADERS,
            json=payload,

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/test_booking.sh (reported line 48)May include surrounding context.

sh
}
EOF

    response=$(curl -s -w "\n%{http_code}" -X POST "$API_ENDPOINT" \
        -H "Content-Type: application/json" \
        -d "{
            \"mobile\": \"$mobile\",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script sends a phone number to a live remote booking API using hardcoded test data, but provides no privacy notice, consent prompt, or warning that personally identifiable information will be transmitted externally. Even though the number appears to be test data, this pattern normalizes sending PII to production-like services and could easily be reused with real customer data during testing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is written entirely in Chinese and gives no indication that users can choose another language or locale. This can violate a language/locale policy when the skill appears to be presented in a fixed language without explicit opt-in or regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This manifest-style JSON stores all user-facing location names, addresses, and transit descriptions in Chinese only. Because SQP-3 applies to all file types and covers forced language or locale without user opt-in, this appears to impose a single locale with no documented choice or justification in the file itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This JSON file contains user-facing service names and descriptions exclusively in Chinese across the listed entries. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language or locale selection is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Line L292 states that the timezone defaults to Beijing time (UTC+8) for time input handling. This is a natural-language locale constraint, and the document does not indicate that users can choose another timezone or explicitly opt in to this behavior.

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 docstring and all runtime prompts are written in Chinese, which imposes a specific language on users. The file does not offer any user opt-in, alternate locale, or documented region-specific justification for this language constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

All comments, prompts, and output messages in the script are in Chinese, including the interactive prompt at L081. This imposes a specific language on users without any opt-in or documented justification, which matches the locale-policy concern described for this rule.

Content

No source excerpt is available for this finding.