← Back to Skills Marketplace
test-vip
by
mikeToBusy
· GitHub ↗
· v1.0.3
· MIT-0
170
Downloads
1
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install test-vip
Description
hahahaha
Usage Guidance
This skill's instructions require running a Python script (query_search_products.py) and calling another skill, but the package contains no script, no declared python requirement, and no information about API endpoints or credentials. Before installing or enabling it: 1) ask the author to provide the missing script or explain where it will be obtained and why it's safe; 2) ask which Python version or other binaries are required and have them declared; 3) ask which external APIs/endpoints are called and whether any credentials are needed; 4) verify the identity and trustworthiness of the 'vipshop-product-consultant' skill the package will invoke; and 5) avoid granting broad network or credential access until those questions are answered. Because this is instruction-only, there's no code to audit — that increases uncertainty about what will actually run at runtime.
Capability Analysis
Type: OpenClaw Skill
Name: test-vip
Version: 1.0.3
The skill bundle is incomplete and potentially vulnerable. It references an external Python script, 'query_search_products.py', which is not included in the provided files, preventing a full security audit of the execution logic. Additionally, the instructions in 'SKILL.md' direct the agent to execute this script via a shell command using an unvalidated '{keyword}' parameter, which presents a command injection vulnerability. The unprofessional description ('hahahaha') in the metadata further suggests a lack of vetting or intentional obfuscation of purpose.
Capability Assessment
Purpose & Capability
The SKILL.md describes a product-search workflow that requires executing a Python script and making HTTP calls, but the skill declares no required binaries (e.g., python), includes no code files (query_search_products.py is referenced but not bundled), and provides no guidance where the script comes from. That mismatch between claimed behavior and required/packaged capabilities is concerning.
Instruction Scope
Runtime instructions explicitly tell the agent to run `python query_search_products.py {keyword}` and to concurrently invoke a separate 'vipshop-product-consultant' skill. Because the referenced script is not included and the nested skill is external, the agent may attempt actions (running local binaries, network calls, invoking other skills) outside the package's visible surface. The instructions do not declare what endpoints, credentials, or data are used or returned.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — nothing is written to disk by an installer. That lowers install-time risk, but raises runtime ambiguity because required binaries/scripts are not packaged.
Credentials
The skill declares no environment variables or credentials, yet it instructs HTTP API calls and running a Python script. If the real implementation requires API keys or other secrets, those are not declared. Lack of declared credentials is inconsistent with typical networked search integrations.
Persistence & Privilege
The skill does not request always:true and has default invocation settings. It does not declare changes to other skills or system config. Autonomous invocation is allowed (platform default) but is not additionally privileged here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install test-vip - After installation, invoke the skill by name or use
/test-vip - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Removed three files: query_search_products.py, search_products.json, and search_response.json.
- SKILL.md updated with a new name and description.
- Dependency section in SKILL.md was simplified.
- Skill functionality for product search and analysis remains, but with reduced implementation details and supporting files.
v1.0.2
- Updated the SKILL.md file for improved formatting and clarity.
- Changed metadata section to YAML front matter.
- Minor edits for organization and readability; no functional changes to the skill logic.
- No file changes detected beyond SKILL.md update.
v1.0.1
- 更新描述,使技能用途更加通用,明确适用于服饰、美妆、母婴等商品搜索场景
- 其余技能执行流程和接口说明保持不变
v1.0.0
vipshop-product 1.0.0 – 商品搜索 Skill 首发版本。
- 支持通过关键词搜索唯品会商品,并抓取TOP5结果。
- 并发调用 vipshop-product-consultant skill,对每个商品生成分析报告。
- 汇总各项数据,自动生成综合分析与购买建议。
- 输出包含商品表格、价格/口碑统计、最优推荐等。
- 搜索与分析高效并发,接口支持JSONP解析。
- 支持简单的 /product-search [keyword] 命令调用。
Metadata
Frequently Asked Questions
What is test-vip?
hahahaha. It is an AI Agent Skill for Claude Code / OpenClaw, with 170 downloads so far.
How do I install test-vip?
Run "/install test-vip" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is test-vip free?
Yes, test-vip is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does test-vip support?
test-vip is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created test-vip?
It is built and maintained by mikeToBusy (@miketobusy); the current version is v1.0.3.
More Skills