技能详情(站内镜像,无评论)
许可证:MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本:v1.0.0
统计:⭐ 0 · 136 · 0 current installs · 0 all-time installs
⭐ 0
安装量(当前) 0
🛡 VirusTotal :可疑 · OpenClaw :可疑
Package:1227323804/check-test
安全扫描(ClawHub)
- VirusTotal :可疑
- OpenClaw :可疑
OpenClaw 评估
The skill's documentation describes a FastAPI REST service with local endpoints and configurable upstream URL/logging, but the included code is only a small client that proxies text to a hardcoded upstream URL (with SSL verification disabled) and does not implement the claimed server behavior — this mismatch and the hardcoded external call are concerning.
目的
The SKILL.md states this is a FastAPI-based REST service (listening on port 8080, /api/safeguard/check, logs, env config), but the shipped code (main.py) contains only a client function (check_sensitive) that posts to a hardcoded upstream URL and a run(params) wrapper. There is no FastAPI app, no HTTP server, and many claimed files/endpoints in SKILL.md (models.py, client.py, logs, .env usage) are absent. The actual capability (proxying conten…
说明范围
SKILL.md instructs running python main.py to start a service and documents API parameters including a userKey, environment variables (SAFEGUARD_API_URL), and logging, but main.py ignores these (hardcoded URL, no env var usage, no logging code). The documentation implies reading/writing logs and exposing endpoints; the code instead performs a network request to an external domain. This is scope creep and a substantive mismatch between instructi…
安装机制
There is no install spec (instruction-only), which lowers install risk. A requirements.txt is included listing requests and urllib3 — reasonable for the client behavior. Nothing is downloaded from arbitrary URLs and no archives are extracted.
证书
SKILL.md documents environment variables (PORT, SAFEGUARD_API_URL, API_TIMEOUT) and describes a userKey parameter for API calls, but the code does not read SAFEGUARD_API_URL or any env vars and instead uses a hardcoded upstream URL. The skill performs outgoing network calls to an external host (safeguard-pre.ucap.com.cn) without declaring required credentials; disabling SSL verification (verify=False) further weakens protection against MITM. T…
持久
The skill does not request special platform privileges (always is false). It does not modify other skills or persist configuration. Autonomous invocation is allowed by default (disable-model-invocation is false) — this is normal but means the skill could be invoked to make network calls if installed.
安装(复制给龙虾 AI)
将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「错敏信息检测」。简介:基于FastAPI的文本错敏信息检测服务,支持敏感词、错别字及规范表述问题检测,提供RESTful API接口。。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/1227323804/check-test/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
# 错敏信息检测 API (Sensitive Content Detection)
一个基于 FastAPI 的错敏信息检测服务,用于检测文本中的敏感词、错别字和规范表述问题。
## 功能特性
- 敏感词检测:识别文本中的敏感词汇
- 错别字检测:发现拼写错误和输入错误
- 规范表述检测:检查专用表述是否符合规范
- RESTful API:简单的 HTTP 接口调用
- 详细日志记录:完整的请求/响应日志
## 快速开始
### 环境要求
- Python 3.11+
- pip
### 安装依赖
```bash
pip install -r requirements.txt
```
### 启动服务
```bash
python main.py
```
服务将在 `http://localhost:8080` 启动。
## API 接口
### 检测接口
**请求**
```
POST /api/safeguard/check
Content-Type: application/json
```
**请求参数**
| 参数 | 类型 | 必填 | 说明 |
|------|------|------|------|
| userKey | string | 是 | 用户密钥 |
| content | string | 是 | 待检测的文本内容 |
| sensitiveCodeList | array | 否 | 指定检测的错敏类型 |
**请求示例**
```json
{
"userKey": "your-user-key",
"content": "这是一段需要检测的文本"
}
```
**响应示例**
```json
{
"code": 0,
"message": "ok",
"content": [
{
"sentencePos": 0,
"termPos": 0,
"wrongTerm": "错误的词",
"expectTerms": ["正确的词"],
"errLevel": 3,
"type": 3,
"newType": "A0200E01",
"explain": "错误说明",
"sentence": "错误词所在句子",
"newTypeMeaning": "错误类型含义"
}
]
}
```
**响应字段说明**
| 字段 | 类型 | 说明 |
|------|------|------|
| code | number | 响应码,0表示成功,1表示失败 |
| message | string | 响应消息 |
| content | array | 检测到的问题列表 |
### 其他接口
| 接口 | 方法 | 说明 |
|------|------|------|
| `/` | GET | 服务信息 |
| `/health` | GET | 健康检查 |
| `/docs` | GET | API 文档(Swagger UI) |
## 配置说明
### 环境变量
| 变量 | 默认值 | 说明 |
|------|--------|------|
| PORT | 8080 | 服务监听端口 |
| SAFEGUARD_API_URL | https://safeguard-pre.ucap.com.cn/... | 上游API地址 |
| API_TIMEOUT | 30 | API请求超时时间(秒) |
## 日志
日志文件位于 `logs/app.log`,记录了:
- 服务启动/关闭信息
- 每个请求的详细信息
- 上游API调用情况
- 错误和异常信息
## 使用示例
### cURL
```bash
curl -X POST "http://localhost:8080/api/safeguard/check"
-H "Content-Type: application/json"
-d '{
"userKey": "your-key",
"content": "待检测文本"
}'
```
### Python
```python
import requests
response = requests.post(
"http://localhost:8080/api/safeguard/check",
json={
"userKey": "your-key",
"content": "待检测文本"
}
)
print(response.json())
```
### JavaScript
```javascript
fetch("http://localhost:8080/api/safeguard/check", {
method: "POST",
headers: {"Content-Type": "application/json"},
body: JSON.stringify({
userKey: "your-key",
content: "待检测文本"
})
})
.then(res => res.json())
.then(data => console.log(data));
```
## 项目结构
```
python-app/
├── main.py # 主应用文件
├── models.py # 数据模型定义
├── client.py # HTTP客户端(已废弃)
├── service.py # 业务服务(已废弃)
├── requirements.txt # 依赖清单
├── .env # 环境变量配置
├── logs/ # 日志目录
│ └── app.log # 应用日志
└── SKILL.md # 本文件
```
## 许可证
MIT License