by 安全扫描
OpenClaw
安全
high confidenceThe skill's code and runtime instructions match its stated purpose (scraping Baidu search results with no credentials), with only minor non-security inconsistencies to note.
评估建议
This skill is coherent with its stated purpose but review these points before installing: (1) ensure you are comfortable with the agent making outbound HTTP requests to baidu.com and to any real URLs the scraper resolves (those third-party sites will see your agent's network identity); (2) the script depends on Python packages (requests, beautifulsoup4) that are not declared — install them in the environment before use; (3) package.json is present but irrelevant (this is a Python script); (4) sc...详细分析 ▾
✓ 用途与能力
The name/description (free Baidu web search) aligns with the included Python script which scrapes baidu.com and supports time-range filtering and result count. Requiring python3 is appropriate. There are no unrelated credential or config requests.
ℹ 指令范围
SKILL.md tells the agent to run the provided Python script with a JSON arg; the script only performs HTTP requests to Baidu and resolves Baidu redirect links (may follow HEAD redirects to obtain the real URL). It does not read local files or environment variables. One operational note: resolving redirects can cause the agent to make additional network requests to third-party destinations (the real target URLs), which will expose the agent's network identity to those sites — expected behavior for a scrapper but worth being aware of.
ℹ 安装机制
No install spec (instruction-only) and no network downloads — low install risk. Minor inconsistency: package.json is present (Node metadata) while the tool is Python; also Python runtime dependencies (requests, bs4/beautifulsoup4) are used but not declared in SKILL.md or a requirements file.
✓ 凭证需求
The skill requests no environment variables or credentials, which is appropriate. It does require network access to baidu.com (and to resolved target URLs). Nothing in the skill asks for unrelated secrets or wide system access.
✓ 持久化与权限
always is false and the skill does not request persistent system-wide changes. The script's shebang contains an absolute path to a local virtualenv (/home/guoxh/...), which appears to be a leftover and does not grant privileges — the script will run when invoked with the python binary on PATH.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/4/16
Initial release of baidu-search-free—free Baidu web search with time filtering, no API key needed. - Search Baidu for web results in Chinese or English - No authentication or API key required; ready to use - Supports time range filtering and custom date ranges - Set number of results to return (up to 50) - Includes anti-scraping retry mechanism for reliability - Returns title, snippet, real URL, and publish time for each result
● Pending
安装命令
点击复制官方npx clawhub@latest install baidu-search-free
镜像加速npx clawhub@latest install baidu-search-free --registry https://cn.longxiaskill.com
技能文档
Free Baidu web search tool, no API key or authentication required, ready to use out of box.
Features
✅ No API key required, completely free ✅ Supports Chinese/English search queries ✅ Time range filtering: 1 day/1 week/1 month/1 year/custom date range ✅ Customizable result count (up to 50 results) ✅ Automatic anti-scraping handling with retry mechanism ✅ Returns title, snippet, real URL, and publish timeUsage
python scripts/search.py '{"query": "your search keywords", "count": 10, "freshness": "pd/pw/pm/py/YYYY-MM-DDtoYYYY-MM-DD"}'
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| query | string | yes | - | Search keywords |
| count | int | no | 10 | Number of results to return, max 50 |
| freshness | string | no | null | Time range filter: pd(past 24h), pw(past week), pm(past month), py(past year), or custom date range in format YYYY-MM-DDtoYYYY-MM-DD |
Example
python scripts/search.py '{"query": "Linzhi Tibet travel guide", "count": 3, "freshness": "pm"}'