← Back to Skills Marketplace
352
Downloads
11
Stars
0
Active Installs
6
Versions
Install in OpenClaw
/install vinrecognition
Description
对车架号/VIN 图片做识别并返回 VIN 及品牌厂家等信息。当用户说：拍了一张车架号照片帮我识别、从图里读出 VIN，或类似 VIN 图片识别时，使用本技能。
Usage Guidance
This skill appears to do exactly what it claims: convert a provided image (or base64) to base64 and send it to JisuAPI's VIN recognition endpoint using your JISU_API_KEY. Before installing, consider: 1) Privacy: images are uploaded to a third-party service (jisuapi.com) — do not send images containing sensitive personal data unless you are comfortable with that provider's policies. 2) API key management: obtain an AppKey from jisuapi.com, store it in JISU_API_KEY, and rotate/revoke if it is accidentally shared. 3) Dependencies: ensure Python3 and the 'requests' package are available in the agent runtime. 4) Limits & costs: check JisuAPI rate limits, quotas, and billing. If any of these are unacceptable, do not install or use the skill.
Capability Analysis
Type: OpenClaw Skill
Name: vinrecognition
Version: 1.0.5
The skill bundle provides a legitimate interface for VIN recognition using the JisuAPI. The Python script (vinrecognition.py) includes security measures such as path normalization and validation to prevent directory traversal attacks when reading local image files. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
The skill name/description (VIN recognition) matches the behavior: vinrecognition.py encodes an image and POSTs to https://api.jisuapi.com/vinrecognition/recognize using an AppKey (JISU_API_KEY). One minor note: the Python script uses the 'requests' library but the SKILL.md / metadata do not declare that dependency or an install step.
Instruction Scope
SKILL.md instructs saving the image locally or passing base64 and calling the script; the script only reads the provided image (or the provided base64) and sends it to the documented JisuAPI endpoint. The script deliberately restricts local path reads to the current working directory and forbids absolute paths or path traversal, and it does not access other env vars, system files, or unexpected endpoints.
Install Mechanism
There is no installer or remote download; this is instruction + a single bundled Python script. No external archives or installers are fetched. As noted above, the runtime requires the 'requests' Python package which is not listed in metadata; this is an operational omission but not a sign of malicious behavior.
Credentials
Only one environment variable is required: JISU_API_KEY (declared as primaryEnv). That matches the API provider usage and is proportionate to the stated purpose. No other secrets or unrelated credentials are requested.
Persistence & Privilege
The skill does not request permanent/always inclusion (always: false), does not modify other skills or global agent settings, and does not attempt to persist credentials or change system-wide configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install vinrecognition - After installation, invoke the skill by name or use
/vinrecognition - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.5
No code changes detected in this version.
- Updated documentation for clarity and detail, especially around API provider introduction and usage instructions
- Added a new introductory section about 极速数据 (JisuAPI) and the categories of APIs they provide
- Improved instructions on how to obtain and configure the required API key (AppKey)
- Enhanced recommended use case descriptions and added context for ideal skill application
- No changes to the core logic or API interface
v1.0.4
- No file changes detected in this version.
- No user-facing changes or updates.
- Behavior and documentation remain the same as the previous version.
v1.0.3
No changes detected in this version.
- No code or documentation updates were made.
- Functionality and usage remain unchanged.
v1.0.2
- No code or documentation changes detected in this release.
- Version update, no functional or content modifications.
v1.0.1
- Updated documentation to correct the script file path from skill/vinrecognition/vinrecognition.py to skills/vinrecognition/vinrecognition.py.
- All usage examples and references now use the new path.
v1.0.0
- Initial release of jisu-vinrecognition skill, supporting OCR recognition of vehicle VIN from windshield or registration certificate images.
- Returns VIN, validity flag, brand, and manufacturer using Jisu VIN Recognition API.
- Supports input via local image file path or base64-encoded image content.
- Standardized error handling with descriptive error codes.
- Environment variable JISU_API_KEY required for API access.
Metadata
Frequently Asked Questions
What is VIN Recognition OCR - VIN识别?
对车架号/VIN 图片做识别并返回 VIN 及品牌厂家等信息。当用户说：拍了一张车架号照片帮我识别、从图里读出 VIN，或类似 VIN 图片识别时，使用本技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 352 downloads so far.
How do I install VIN Recognition OCR - VIN识别?
Run "/install vinrecognition" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is VIN Recognition OCR - VIN识别 free?
Yes, VIN Recognition OCR - VIN识别 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does VIN Recognition OCR - VIN识别 support?
VIN Recognition OCR - VIN识别 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created VIN Recognition OCR - VIN识别?
It is built and maintained by 极速数据 (@jisuapi); the current version is v1.0.5.
More Skills