← 返回 Skills 市场
Querit Web Search
作者
MurphyZzzzz
· GitHub ↗
· v1.0.1
382
总下载
3
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install querit-web-search
功能描述
Advanced web search using the Querit API with support for site filtering, time ranges, geolocation, and language targeting.
安全使用建议
This skill appears to do what it says: run a Python script that sends your query to Querit's API using QUERIT_API_KEY. Before installing, consider: (1) QUERIT_API_KEY will be sent to an external service—only provide keys you trust and consider scoping/rotating the key; (2) the runtime must have Python and the 'requests' package installed or the script will fail; (3) any query text (including potentially sensitive information) will be transmitted to api.querit.ai, so avoid sending secrets; (4) review Querit's privacy and data-retention policies if you will send private data; (5) because the skill can be invoked by the agent, ensure you are comfortable with outbound network calls being made automatically. If you want extra safety, restrict the API key's permissions and monitor usage in the Querit dashboard.
功能分析
Type: OpenClaw Skill
Name: querit-web-search
Version: 1.0.1
The skill is designed for advanced web search via the Querit API. The `SKILL.md` provides clear instructions for the agent to execute the `search.py` script with a JSON payload. The `search.py` script correctly retrieves the `QUERIT_API_KEY` from environment variables, parses the input as JSON, and makes a secure POST request to a hardcoded `https://api.querit.ai/v1/search` endpoint using the `requests` library. There is no evidence of arbitrary code execution, file system manipulation, data exfiltration to unauthorized endpoints, or malicious prompt injection attempts within the `SKILL.md` instructions. The input handling in `search.py` is robust against shell injection, as it treats the input as JSON for an API call, not as a shell command.
能力评估
Purpose & Capability
Name/description, required binary (python3), and required env var (QUERIT_API_KEY) match the included script's behavior (it issues HTTPS POSTs to Querit's API). No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to run the included Python script with a JSON string or plain query. The script only reads argv and the QUERIT_API_KEY env var and issues an HTTPS request to the hardcoded Querit endpoint; it does not read other files, system config, or extraneous environment variables.
Install Mechanism
No install spec (instruction-only) which lowers risk. One caveat: the script imports 'requests' but the skill does not declare an installation step to ensure the 'requests' package is present; this is an operational issue (not a security incoherence) and may cause runtime failures if the runtime lacks that package.
Credentials
Only QUERIT_API_KEY is required and is the primary credential; this is proportional to a service that authenticates to an external search API. No unrelated secrets or multiple credentials are requested.
Persistence & Privilege
Skill does not request always:true, does not modify other skills or system settings, and does not persist data locally. It simply performs network requests at runtime.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install querit-web-search - 安装完成后,直接呼叫该 Skill 的名称或使用
/querit-web-search触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
- Renamed skill from querit-search to querit-web-search.
v1.0.0
- Migrated from a JavaScript/Node.js implementation to a single Python script (`search.py`).
- Removed old files including README, JSON metadata, shell installer, and JavaScript search/content extractors.
- Updated documentation to focus on Python usage with structured JSON input for advanced filtering (site, language, date, country).
- Clarified setup, trigger conditions, and execution examples for real-time web searches using the Querit API.
- Expanded filter capabilities and simplified installation requirements (now needs Python and `QUERIT_API_KEY`).
元数据
常见问题
Querit Web Search 是什么?
Advanced web search using the Querit API with support for site filtering, time ranges, geolocation, and language targeting. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 382 次。
如何安装 Querit Web Search?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install querit-web-search」即可一键安装,无需额外配置。
Querit Web Search 是免费的吗?
是的,Querit Web Search 完全免费(开源免费),可自由下载、安装和使用。
Querit Web Search 支持哪些平台?
Querit Web Search 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Querit Web Search?
由 MurphyZzzzz(@murphyzzzzz)开发并维护,当前版本 v1.0.1。
推荐 Skills