Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

TencentCloud VehicleLicense OCR

v1.0.3

腾讯云行驶证识别(VehicleLicenseOCR)接口调用技能。当用户需要识别行驶证图片主页(车牌号码、车辆类型、所有人、住址、使用性质、品牌型号、识别代码、发动机号、注册日期、发证日期)或副页(号牌号码、档案编号、核定载人数、总质量、整备质量、核定载质量、外廓尺寸、准牵引总质量、备注、检验记录)信息时,应使...

0· 375·2 current·2 all-time
bytencent-ocr@zt1314p-design

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zt1314p-design/tencentcloud-ocr-vehiclelicense.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "TencentCloud VehicleLicense OCR" (zt1314p-design/tencentcloud-ocr-vehiclelicense) from ClawHub.
Skill page: https://clawhub.ai/zt1314p-design/tencentcloud-ocr-vehiclelicense
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install zt1314p-design/tencentcloud-ocr-vehiclelicense

ClawHub CLI

Package manager switcher

npx clawhub@latest install tencentcloud-ocr-vehiclelicense
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name, description, SKILL.md and scripts/main.py consistently implement Tencent Cloud VehicleLicenseOCR: calling the Tencent OCR API, accepting ImageUrl or Base64, and returning parsed fields. The required network access to ocr.tencentcloudapi.com and the tencentcloud-sdk-python dependency are coherent with the stated purpose.
Instruction Scope
Runtime instructions and the script confine behavior to constructing an OCR request and printing parsed results. The skill will transmit image data or image URLs to Tencent Cloud (expected for this service). It reads local files only when the user explicitly supplies a file path or Base64 input. No additional system-wide data collection or unexpected external endpoints are present.
Install Mechanism
No install spec is provided (instruction-only install), but SKILL.md and the script require the third-party Python package tencentcloud-sdk-python installed via pip. That is reasonable for the task but means runtime pip installation from PyPI is expected — verify the package source if you care about supply-chain risk.
!
Credentials
Both SKILL.md and scripts/main.py require Tencent Cloud credentials (TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY), but the registry metadata lists no required environment variables or primary credential. This metadata omission is an incoherence and could mislead users or automation about the sensitive credentials this skill needs. Requesting these cloud credentials is proportionate to the function, but the omission in metadata is a notable red flag.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system-wide privileges or modify other skills. It runs on-demand and requires standard environment variables for the API — no excessive persistence or privilege escalation observed.
What to consider before installing
This skill appears to implement Tencent Cloud VehicleLicenseOCR correctly, but the registry metadata fails to declare the sensitive environment variables the code requires. Before installing or using it: (1) do not set production TencentCloud credentials into an unknown skill — consider creating a limited/test API key; (2) confirm you trust the skill source (there is no homepage) and consider reviewing the included scripts/main.py yourself; (3) be aware that any image URL you provide may be fetched by Tencent (and any Base64 or local file you pass will be uploaded), so avoid passing internal URLs or files containing sensitive data; (4) install tencentcloud-sdk-python from the official PyPI source only and run the script in an isolated environment if possible; (5) ask the publisher to update the registry metadata to list TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY so automated policy checks and users are correctly informed.

Like a lobster shell, security has layers — review code before you run it.

latestvk97e1w116v3p9qqrxx0xc0d8hx82nj01
375downloads
0stars
4versions
Updated 19h ago
v1.0.3
MIT-0

腾讯云行驶证识别 (VehicleLicenseOCR)

用途

调用腾讯云OCR行驶证识别接口,支持行驶证主页和副页所有字段的自动定位与识别,同时支持复印件、翻拍告警功能。

核心能力:

  • 主页(FRONT):识别号牌号码、车辆类型、所有人、住址、使用性质、品牌型号、车辆识别代号、发动机号码、注册日期、发证日期、印章
  • 副页(BACK):识别号牌号码、档案编号、核定人数、总质量、整备质量、核定载质量、外廓尺寸、准牵引总质量、备注、检验记录、副页编码、燃料种类
  • 双面(DOUBLE):同时识别主页和副页
  • 电子行驶证:额外支持状态、检验有效期、生成时间(主页)及住址、发证机关、车身颜色(副页)
  • 拖拉机行驶证:支持拖拉机行驶证副页识别
  • 告警功能:复印件、翻拍件、反光、模糊、边框不完整等5种告警检测

官方文档:https://cloud.tencent.com/document/api/866/36209

使用时机

当用户提出以下需求时触发此技能:

  • 需要从行驶证图片中提取车辆信息
  • 需要识别行驶证主页或副页内容
  • 需要获取车牌号码、车辆类型、所有人、VIN码等行驶证字段
  • 需要检测行驶证是否为复印件、翻拍件
  • 需要识别电子行驶证信息
  • 需要识别拖拉机行驶证信息
  • 涉及行驶证OCR识别的任何场景

环境要求

  • Python 3.6+
  • 依赖:tencentcloud-sdk-python(通过 pip install tencentcloud-sdk-python 安装)
  • 环境变量:
    • TENCENTCLOUD_SECRET_ID:腾讯云API密钥ID
    • TENCENTCLOUD_SECRET_KEY:腾讯云API密钥Key

使用方式

运行 scripts/main.py 脚本完成行驶证识别。

请求参数

参数类型必填说明
ImageBase64str否(二选一)图片Base64值,编码后不超过7M,分辨率建议500*800以上,支持PNG/JPG/JPEG/BMP,建议卡片占图片2/3以上
ImageUrlstr否(二选一)图片URL地址,下载时间不超过3秒,都提供时只使用ImageUrl
CardSidestrFRONT(主页正面,有红色印章) / BACK(副页正面,有号码号牌) / DOUBLE(主副双面),默认FRONT
TractorCardSidestrFRONT(拖拉机行驶证主页) / BACK(拖拉机行驶证副页)
UserAgentstr请求来源标识(可选),用于追踪调用来源,统一固定为Skills

输出格式

识别成功后返回 JSON 格式结果:

主页(FRONT)

{
  "FrontInfo": {
    "PlateNo": "京A12345",
    "VehicleType": "小型轿车",
    "Owner": "张三",
    "Address": "XX省XX市XX区XX路XX号",
    "UseCharacter": "非营运",
    "Model": "大众牌SVW71412SE",
    "Vin": "LSVAM4187C2XXXXXX",
    "EngineNo": "CDF0XXXXX",
    "RegisterDate": "2020-01-01",
    "IssueDate": "2020-01-01",
    "Seal": "XX市公安局交通管理局"
  },
  "VehicleLicenseType": "Normal",
  "RecognizeWarnCode": [],
  "RecognizeWarnMsg": [],
  "RequestId": "xxx"
}

副页(BACK)

{
  "BackInfo": {
    "PlateNo": "京A12345",
    "FileNo": "110100XXXXXXXX",
    "AllowNum": "5人",
    "TotalMass": "1750kg",
    "CurbWeight": "1390kg",
    "LoadQuality": "-",
    "ExternalSize": "4620×1800×1480mm",
    "TotalQuasiMass": "-",
    "Marks": "",
    "Record": "检验有效期至2026年01月",
    "SubPageCode": "110100XXXXXXXX",
    "FuelType": "汽油"
  },
  "VehicleLicenseType": "Normal",
  "RecognizeWarnCode": [],
  "RecognizeWarnMsg": [],
  "RequestId": "xxx"
}

告警码说明

告警码含义消息标识
-9102复印件告警WARN_DRIVER_LICENSE_COPY_CARD
-9103翻拍件告警WARN_DRIVER_LICENSE_SCREENED_CARD
-9104反光告警WARN_DRIVER_LICENSE_REFLECTION
-9105模糊告警WARN_DRIVER_LICENSE_BLUR
-9106边框不完整告警WARN_DRIVER_LICENSE_BORDER_INCOMPLETE

注:告警码可以同时存在多个。

错误码说明

错误码描述
FailedOperation.DownLoadError文件下载失败
FailedOperation.EmptyImageError图片内容为空
FailedOperation.ImageBlur图片模糊
FailedOperation.ImageDecodeFailed图片解码失败
FailedOperation.ImageNoText图片中未检测到文本
FailedOperation.ImageSizeTooLarge图片尺寸过大
FailedOperation.LicenseCardSideErrorCardSide与实际卡证正副页类型不符
FailedOperation.LicenseMultiCardError图片中存在两张及以上同面卡证
FailedOperation.NoVehicleLicenseError上传的图片非行驶证
FailedOperation.OcrFailedOCR识别失败
FailedOperation.UnKnowError未知错误
FailedOperation.UnOpenError服务未开通
InvalidParameter.EngineImageDecodeFailed图片解码失败
InvalidParameterValue.InvalidParameterValueLimit参数值错误
LimitExceeded.TooLargeFileError文件内容太大
ResourceUnavailable.InArrears账号已欠费
ResourceUnavailable.ResourcePackageRunOut账号资源包耗尽
ResourcesSoldOut.ChargeStatusException计费状态异常

调用示例

# 通过URL识别行驶证主页
python scripts/main.py --image-url "https://example.com/vehicle_license.jpg" --card-side FRONT

# 通过URL识别行驶证副页
python scripts/main.py --image-url "https://example.com/vehicle_license_back.jpg" --card-side BACK

# 识别行驶证主页+副页(双面)
python scripts/main.py --image-url "https://example.com/vehicle_license.jpg" --card-side DOUBLE

# 通过Base64识别行驶证(默认主页)
python scripts/main.py --image-base64 "/path/to/vehicle_license.jpg"

# 识别拖拉机行驶证副页
python scripts/main.py --image-url "https://example.com/tractor_license.jpg" --tractor-card-side BACK

# 指定地域
python scripts/main.py --image-url "https://example.com/vehicle_license.jpg" --region ap-beijing```

Comments

Loading comments...